Mingyuan Zhou

ICLR Conference 2025 Conference Paper

Advancing Graph Generation through Beta Diffusion

• Xinyang Liu
• Yilin He
• Bo Chen
• Mingyuan Zhou

Diffusion models have excelled in generating natural images and are now being adapted to a variety of data types, including graphs. However, conventional models often rely on Gaussian or categorical diffusion processes, which can struggle to accommodate the mixed discrete and continuous components characteristic of graph data. Graphs typically feature discrete structures and continuous node attributes that often exhibit rich statistical patterns, including sparsity, bounded ranges, skewed distributions, and long-tailed behavior. To address these challenges, we introduce Graph Beta Diffusion (GBD), a generative model specifically designed to handle the diverse nature of graph data. GBD leverages a beta diffusion process, effectively modeling both continuous and discrete elements. Additionally, we propose a modulation technique that enhances the realism of generated graphs by stabilizing critical graph topology while maintaining flexibility for other components. GBD competes strongly with existing models across multiple general and biochemical graph benchmarks, showcasing its ability to capture the intricate balance between discrete and continuous features inherent in real-world graph data. Our PyTorch code is available at https://github.com/xinyangATK/GraphBetaDiffusion.

ICLR Conference 2025 Conference Paper

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

• Mingyuan Zhou
• Huangjie Zheng
• Yi Gu
• Zhendong Wang 0005
• Hai Huang

Score identity Distillation (SiD) is a data-free method that has achieved state-of-the-art performance in image generation by leveraging only a pretrained diffusion model, without requiring any training data. However, the ultimate performance of SiD is constrained by the accuracy with which the pretrained model captures the true data scores at different stages of the diffusion process. In this paper, we introduce SiDA (SiD with Adversarial Loss), which not only enhances generation quality but also improves distillation efficiency by incorporating real images and adversarial loss. SiDA utilizes the encoder from the generator's score network as a discriminator, allowing it to distinguish between real images and those generated by SiD. The adversarial loss is batch-normalized within each GPU and then combined with the original SiD loss. This integration effectively incorporates the average "fakeness" per GPU batch into the pixel-based SiD loss, enabling SiDA to distill a single-step generator. SiDA converges significantly faster than its predecessor when distilled from scratch, and swiftly improves upon the original model's performance during fine-tuning from a pre-distilled SiD generator. This one-step adversarial distillation method establishes new benchmarks in generation performance when distilling EDM diffusion models, achieving FID scores of **1.499** on CIFAR-10 unconditional, **1.396** on CIFAR-10 conditional, and **1.110** on ImageNet 64x64. When distilling EDM2 models trained on ImageNet 512x512, our SiDA method surpasses even the largest teacher model, EDM2-XXL, which achieved an FID of 1.81 using classifier-free guidance (CFG) and 63 generation steps. Specifically, SiDA achieves FID scores of **2.156** for size XS, **1.669** for S, **1.488** for M, **1.413** for L, **1.379** for XL, and **1.366** for XXL, all without CFG and in a single generation step. These results highlight substantial improvements across all model sizes. Our code and checkpoints are available at https://github.com/mingyuanzhou/SiD/tree/sida.

TMLR Journal 2025 Journal Article

Diverse Condensed Data Generation via Class Preserving Distribution Matching

• DanDan Guo
• Zhuo Li
• He Zhao
• Mingyuan Zhou
• Hongyuan Zha

Large-scale datasets for training many real-world machine learning models pose significant computational resource challenges. One approach to mitigate this is via data condensation, which aims at learning a small dataset but still sufficiently capturing the rich information in the original one. Most of existing approaches learn the condensed dataset and task-related model parameters (e.g., classifier) in a bi-level meta-learning way. The recently proposed distribution matching (DM), however, avoids the expensive bi-level optimization but ignores task-related models. This work proposes a novel class preserving DM framework consisting of two key components. The first one is responsible for capturing the original data distribution of each class based on energy distance, which can encourage the diversity in the generated synthetic data. The other is classifier-critic constraint, which forces the learned synthetic samples to fit pre-trained task-related models, such as an off-the-shelf classifier. Designing the optimization loss in this way, we can generate more diverse and class preserving distilled data without the bi-level optimization. Extensive experiments reveal that our method can produce more effective condensed data for downstream tasks with less training cost and can also be successfully applied to de-biased dataset condensation.

ICLR Conference 2025 Conference Paper

DRL: Decomposed Representation Learning for Tabular Anomaly Detection

• Hangting Ye
• He Zhao 0001
• Wei Fan 0010
• Mingyuan Zhou
• Dandan Guo
• Yi Chang 0001

Anomaly detection, indicating to identify the anomalies that significantly deviate from the majority normal instances of data, has been an important role in machine learning and related applications. Despite the significant success achieved in anomaly detection on image and text data, the accurate Tabular Anomaly Detection (TAD) has still been hindered due to the lack of clear prior semantic information in the tabular data. Most state-of-the-art TAD studies are along the line of reconstruction, which first reconstruct training data and then use reconstruction errors to decide anomalies; however, reconstruction on training data can still hardly distinguish anomalies due to the data entanglement in their representations. To address this problem, in this paper, we propose a novel approach Decomposed Representation Learning (DRL), to re-map data into a tailor-designed constrained space, in order to capture the underlying shared patterns of normal samples and differ anomalous patterns for TAD. Specifically, we enforce the representation of each normal sample in the latent space to be decomposed into a weighted linear combination of randomly generated orthogonal basis vectors, where these basis vectors are both data-free and training-free. Furthermore, we enhance the discriminative capability between normal and anomalous patterns in the latent space by introducing a novel constraint that amplifies the discrepancy between these two categories, supported by theoretical analysis. Finally, extensive experiments on 40 tabular datasets and 16 competing tabular anomaly detection algorithms show that our method achieves state-of-the-art performance.

ICLR Conference 2025 Conference Paper

Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer

• Xinyue Hu
• Zhibin Duan
• Bo Chen 0001
• Mingyuan Zhou

Although deep neural networks have demonstrated significant success due to their powerful expressiveness, most models struggle to meet practical requirements for uncertainty estimation. Concurrently, the entangled nature of deep neural net- works leads to a multifaceted problem, where various localized explanation tech- niques reveal that multiple unrelated features influence the decisions, thereby un- dermining interpretability. To address these challenges, we develop a Bayesian Nonnegative Decision Layer (BNDL), which reformulates deep neural networks as a conditional Bayesian non-negative factor analysis. By leveraging stochastic latent variables, the BNDL can model complex dependencies and provide robust uncertainty estimation. Moreover, the sparsity and non-negativity of the latent variables encourage the model to learn disentangled representations and decision layers, thereby improving interpretability. We also offer theoretical guarantees that BNDL can achieve effective disentangled learning. In addition, we developed a corresponding variational inference method utilizing a Weibull variational in- ference network to approximate the posterior distribution of the latent variables. Our experimental results demonstrate that with enhanced disentanglement capa- bilities, BNDL not only improves the model’s accuracy but also provides reliable uncertainty estimation and improved interpretability.

NeurIPS Conference 2025 Conference Paper

Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting

• Ruyi An
• haicheng huang
• Huangjie Zheng
• Mingyuan Zhou

Generative data augmentation (GDA) leverages generative models to enrich training sets with entirely new samples drawn from the modeled data distribution to achieve performance gains. However, the usage of the mighty contemporary diffusion models in GDA remains impractical: *i)* their thousand-step sampling loop inflates wall-time and energy cost per image augmentation; and *ii)* the divergence between synthetic and real distributions is unknown--classifiers trained on synthetic receive biased gradients. We propose DAR-GDA, a three-stage augmentation pipeline that unites model **D**istillation, **A**dversarial alignment, and importance **R**eweighting that makes diffusion-quality augmentation both fast and optimized for improving downstream learning outcomes. In particular, a teacher diffusion model is compressed into a one-step student via score distillation, slashing the time per-image cost by $>100\times$ while preserving FID. During this distillation (D), the student model additionally undergoes adversarial alignment (A) by receiving direct training signals against real images, supplementing the teacher's guidance to better match the true data distribution. The discriminator from this adversarial process inherently learns to assess the synthetic-to-real data gap. Its calibrated probabilistic outputs are then employed in reweighting (R) by importance weights that quantify the distributional gap and adjust the classification loss when training downstream models; we show that reweighting yields an unbiased stochastic estimator of the real-data risk, fostering training dynamics akin to those of genuine samples. Experiments validate DAR-GDA's synergistic design through progressive accuracy gains with each D-A-R stage. Our approach not only surpasses conventional non-foundation-model GDA baselines but also remarkably matches or exceeds the GDA performance of large, web-pretrained text-to-image models, despite using solely in-domain data. DAR-GDA thus offers diffusion-fidelity GDA samples efficiently, while correcting synthetic-to-real bias to benefit downstream tasks.

NeurIPS Conference 2025 Conference Paper

Generative Model Inversion Through the Lens of the Manifold Hypothesis

• Xiong Peng
• Bo Han
• Fengfei Yu
• Tongliang Liu
• Feng Liu
• Mingyuan Zhou

Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models. Recent generative MIAs utilize generative adversarial networks to learn image priors that guide the inversion process, yielding reconstructions with high visual quality and strong fidelity to the private data. To explore the reason behind their effectiveness, we begin by examining the gradients of inversion loss w. r. t. synthetic inputs, and find that these gradients are surprisingly noisy. Further analysis shows that generative model inversion approaches implicitly denoise the gradients by projecting them onto the tangent space of the generator manifold—filtering out directions that deviate from the manifold structure while preserving informative components aligned with it. Our empirical measurements show that, in models trained with standard supervision, loss gradients exhibit large angular deviations from the data manifold, indicating poor alignment with class-relevant directions. This observation motivates our central hypothesis: models become more vulnerable to MIAs when their loss gradients align more closely with the generator manifold. We validate this hypothesis by designing a novel training objective that explicitly promotes such alignment. Building on this insight, we further introduce a training-free approach to enhance gradient–manifold alignment during inversion, leading to consistent improvements over state-of-the-art generative MIAs.

ICLR Conference 2025 Conference Paper

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

• Mingyuan Zhou
• Zhendong Wang 0005
• Huangjie Zheng
• Hai Huang

Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is their slow sample generation process, which requires iterative refinement through the same network. To overcome this, we introduce a data-free guided distillation method that enables the efficient distillation of pretrained Stable Diffusion models without access to the real training data, often restricted due to legal, privacy, or cost concerns. This method enhances Score identity Distillation (SiD) with Long and Short Classifier-Free Guidance (LSG), an innovative strategy that applies Classifier-Free Guidance (CFG) not only to the evaluation of the pretrained diffusion model but also to the training and evaluation of the fake score network. We optimize a model-based explicit score matching loss using a score-identity-based approximation alongside our proposed guidance strategies for practical computation. By exclusively training with synthetic images generated by its one-step generator, our data-free distillation method rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Notably, the one-step distillation of Stable Diffusion 1.5 achieves an FID of **8.15** on the COCO-2014 validation set, a record low value under the data-free setting. Our code and checkpoints are available at https://github.com/mingyuanzhou/SiD-LSG.

NeurIPS Conference 2025 Conference Paper

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

• Yifan Sun
• Jingyan Shen
• Yibin Wang
• Tianyu Chen
• Zhendong Wang
• Mingyuan Zhou
• Huan ZHang

Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs), particularly to enhance their reasoning capabilities. However, RL fine-tuning remains highly resource-intensive, and existing work has largely overlooked the problem of data efficiency. In this paper, we propose two techniques to improve data efficiency in LLM RL fine-tuning: difficulty-targeted online data selection and rollout replay. We introduce the notion of adaptive difficulty to guide online data selection, prioritizing questions of moderate difficulty that are more likely to yield informative learning signals. To estimate adaptive difficulty efficiently, we develop an attention-based framework that requires rollouts for only a small reference set of questions. The adaptive difficulty of the remaining questions is then estimated based on their similarity to this set. To further reduce rollout cost, we introduce a rollout replay mechanism inspired by experience replay in traditional RL. This technique reuses recent rollouts, lowering per-step computation while maintaining stable updates. Experiments across 6 LLM-dataset combinations show that our method reduces RL fine-tuning time by 23% to 62% while reaching the same level of performance as the original GRPO algorithm. Our code repository is available at https: //github. com/ASTRAL-Group/data-efficient-llm-rl/.

ICML Conference 2025 Conference Paper

OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation

• Yaoxuan Feng
• Wenchao Chen
• Yuxin Li 0003
• Bo Chen 0001
• Yubiao Wang
• Zixuan Zhao
• Hongwei Liu 0001
• Mingyuan Zhou

Diffusion models have demonstrated outstanding performance in industrial anomaly detection. However, their iterative denoising nature results in slow inference speed, limiting their practicality for real-time industrial deployment. To address this challenge, we propose OmiAD, a one-step masked diffusion model for multi-class anomaly detection, derived from a well-designed multi-step A daptive M asked D iffusion M odel (AMDM) and compressed using A dversarial S core D istillation (ASD). OmiAD first introduces AMDM, equipped with an adaptive masking strategy that dynamically adjusts masking patterns based on noise levels and encourages the model to reconstruct anomalies as normal counterparts by leveraging broader context, to reduce the pixel-level shortcut reliance. Then, ASD is developed to compress the multi-step diffusion process into a single-step generator by score distillation and incorporating a shared-weight discriminator effectively reusing parameters while significantly improving both inference efficiency and detection performance. The effectiveness of OmiAD is validated on four diverse datasets, achieving state-of-the-art performance across seven metrics while delivering a remarkable inference speedup.

ICML Conference 2025 Conference Paper

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

• Zhendong Wang 0005
• Max Li
• Ajay Mandlekar
• Zhenjia Xu
• Jiaojiao Fan
• Yashraj Narang
• Linxi Fan
• Yuke Zhu

Diffusion models, praised for their success in generative tasks, are increasingly being applied to robotics, demonstrating exceptional performance in behavior cloning. However, their slow generation process stemming from iterative denoising steps poses a challenge for real-time applications in resource-constrained robotics setups and dynamically changing environments. In this paper, we introduce the One-Step Diffusion Policy (OneDP), a novel approach that distills knowledge from pre-trained diffusion policies into a single-step action generator, significantly accelerating response times for robotic control tasks. We ensure the distilled generator closely aligns with the original policy distribution by minimizing the Kullback-Leibler (KL) divergence along the diffusion chain, requiring only $2%$-$10%$ additional pre-training cost for convergence. We evaluated OneDP on 6 challenging simulation tasks as well as 4 self-designed real-world tasks using the Franka robot. The results demonstrate that OneDP not only achieves state-of-the-art success rates but also delivers an order-of-magnitude improvement in inference speed, boosting action prediction frequency from 1. 5 Hz to 62 Hz, establishing its potential for dynamic and computationally constrained robotic applications. A video demo is provided at our project page, and the code will be publicly available.

ICLR Conference 2025 Conference Paper

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

• Tianqi Chen
• Shujian Zhang
• Mingyuan Zhou

The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and trustworthy GenAI models. Traditional MU methods often rely on stringent assumptions and require access to real data. This paper introduces Score Forgetting Distillation (SFD), an innovative MU approach that promotes the forgetting of undesirable information in diffusion models by aligning the conditional scores of "unsafe" classes or concepts with those of "safe" ones. To eliminate the need for real data, our SFD framework incorporates a score-based MU loss into the score distillation objective of a pretrained diffusion model. This serves as a regularization term that preserves desired generation capabilities while enabling the production of synthetic data through a one-step generator. Our experiments on pretrained label-conditional and text-to-image diffusion models demonstrate that our method effectively accelerates the forgetting of target classes or concepts during generation, while preserving the quality of other classes or concepts. This unlearned and distilled diffusion not only pioneers a novel concept in MU but also accelerates the generation speed of diffusion models. Our experiments and studies on a range of diffusion models and datasets confirm that our approach is generalizable, effective, and advantageous for MU in diffusion models. Code is available at [https://github.com/tqch/score-forgetting-distillation](https://github.com/tqch/score-forgetting-distillation). (**Warning:** This paper contains sexually explicit imagery, discussions of pornography, racially-charged terminology, and other content that some readers may find disturbing, distressing, and/or offensive.)

TMLR Journal 2025 Journal Article

Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model

• Yueqin Yin
• Shentao Yang
• Yujia Xie
• Ziyi Yang
• Yuting Sun
• Hany Hassan Awadalla
• Weizhu Chen
• Mingyuan Zhou

Reinforcement learning from human feedback (RLHF) has been widely adopted to align language models (LMs) with human preference. Previous RLHF works typically take a bandit formulation, which, though intuitive, ignores the sequential nature of LM generation and can suffer from the sparse reward issue. While recent works propose dense token-level RLHF, treating each token as an action may be oversubtle to proper reward assignment. In this paper, we seek to get the best of both by training and utilizing a segment-level reward model, which assigns a reward to each semantically complete text segment that spans over a short sequence of tokens. For reward learning, our method allows dynamic text segmentation and compatibility with standard sequence-preference datasets. For effective RL-based LM training against segment reward, we generalize the classical scalar bandit reward normalizers into location-aware normalizer functions and interpolate the segment reward for further densification. Our method performs competitively on three popular RLHF benchmarks for LM policy: AlpacaEval 2.0, Arena-Hard, and MT-Bench. Ablation studies are conducted to further demonstrate our method.

NeurIPS Conference 2025 Conference Paper

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

• Xun Huang
• Zhengqi Li
• Guande He
• Mingyuan Zhou
• Eli Shechtman

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs during inference. Unlike prior methods that denoise future frames based on ground-truth context frames, Self Forcing conditions each frame's generation on previously self-generated outputs by performing autoregressive rollout with key-value (KV) caching during training. This strategy enables supervision through a holistic loss at the video level that directly evaluates the quality of the entire generated sequence, rather than relying solely on traditional frame-wise objectives. To ensure training efficiency, we employ a few-step diffusion model along with a stochastic gradient truncation strategy, effectively balancing computational cost and performance. We further introduce a rolling KV cache mechanism that enables efficient autoregressive video extrapolation. Extensive experiments demonstrate that our approach achieves real-time streaming video generation with sub-second latency on a single GPU, while matching or even surpassing the generation quality of significantly slower and non-causal diffusion models.

ICML Conference 2024 Conference Paper

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference

• Shentao Yang
• Tianqi Chen
• Mingyuan Zhou

Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data, these methods are developed under the bandit assumption of a latent reward on the entire diffusion reverse chain, while ignoring the sequential nature of the generation process. This may harm the efficacy and efficiency of preference alignment. In this paper, we take on a finer dense reward perspective and derive a tractable alignment objective that emphasizes the initial steps of the T2I reverse chain. In particular, we introduce temporal discounting into DPO-style explicit-reward-free objectives, to break the temporal symmetry therein and suit the T2I generation hierarchy. In experiments on single and multiple prompt generation, our method is competitive with strong relevant baselines, both quantitatively and qualitatively. Further investigations are conducted to illustrate the insight of our approach. Source code is available at https: //github. com/Shentao-YANG/Dense_Reward_T2I.

NeurIPS Conference 2024 Conference Paper

Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning

• Tianyu Chen
• Zhendong Wang
• Mingyuan Zhou

Offline reinforcement learning (RL) leverages pre-collected datasets to train optimal policies. Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressive policy class, significantly boosts the performance of offline RL. However, its reliance on iterative denoising sampling to generate actions slows down both training and inference. While several recent attempts have tried to accelerate diffusion-QL, the improvement in training and/or inference speed often results in degraded performance. In this paper, we introduce a dual policy approach, Diffusion Trusted Q-Learning (DTQL), which comprises a diffusion policy for pure behavior cloning and a practical one-step policy. We bridge the two polices by a newly introduced diffusion trust region loss. The diffusion policy maintains expressiveness, while the trust region loss directs the one-step policy to explore freely and seek modes within the region defined by the diffusion policy. DTQL eliminates the need for iterative denoising sampling during both training and inference, making it remarkably computationally efficient. We evaluate its effectiveness and algorithmic characteristics against popular Kullback-Leibler (KL) based distillation methods in 2D bandit scenarios and gym tasks. We then show that DTQL could not only outperform other methods on the majority of the D4RL benchmark tasks but also demonstrate efficiency in training and inference speeds. The PyTorch implementation is available at https: //github. com/TianyuCodings/Diffusion Trusted Q_Learning.

TMLR Journal 2024 Journal Article

Hashing with Uncertainty Quantification via Sampling-based Hypothesis Testing

• Yucheng Wang
• Mingyuan Zhou
• Xiaoning Qian

To quantify different types of uncertainty when deriving hash-codes for image retrieval, we develop a probabilistic hashing model(ProbHash). Sampling-based hypothesis testing is then derived for hashing with uncertainty quantification(HashUQ) in ProbHash to improve the granularity of hashing-based retrieval by prioritizing the data with confident hash-codes. HashUQ can drastically improve the retrieval performance without sacrificing computational efficiency. For efficient deployment of HashUQ in real-world applications, we discretize the quantified uncertainty to reduce the potential storage overhead. Experimental results show that our HashUQ can achieve state-of-the-art retrieval performance on three image datasets. Ablation experiments on model hyperparameters, different model components, and effects of UQ are also provided with performance comparisons. Our code is available at https://github.com/QianLab/HashUQ.

ICLR Conference 2024 Conference Paper

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling

• Huangjie Zheng
• Zhendong Wang 0005
• Jianbo Yuan
• Guanghan Ning
• Pengcheng He
• Quanzeng You
• Hongxia Yang
• Mingyuan Zhou

Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these computational challenges, a less-explored issue is designing an efficient and adaptable network backbone for iterative refinement. Current options like U-Net and Vision Transformer often rely on resource-intensive deep networks and lack the flexibility needed for generating images at variable resolutions or with a smaller network than used in training. This study introduces LEGO bricks, which seamlessly integrate Local-feature Enrichment and Global-content Orchestration. These bricks can be stacked to create a test-time reconfigurable diffusion backbone, allowing selective skipping of bricks to reduce sampling costs and generate higher-resolution images than the training data. LEGO bricks enrich local regions with an MLP and transform them using a Transformer block while maintaining a consistent full-resolution image across all bricks. Experimental results demonstrate that LEGO bricks enhance training efficiency, expedite convergence, and facilitate variable-resolution image generation while maintaining strong generative performance. Moreover, LEGO significantly reduces sampling time compared to other methods, establishing it as a valuable enhancement for diffusion models. Our code and project page are available at https://jegzheng.github.io/LEGODiffusion.

ICLR Conference 2024 Conference Paper

Long-tailed Diffusion Models with Oriented Calibration

• Tianjiao Zhang
• Huangjie Zheng
• Jiangchao Yao
• Xiangfeng Wang 0001
• Mingyuan Zhou
• Ya Zhang 0002
• Yanfeng Wang 0001

Diffusion models are acclaimed for generating high-quality and diverse images. However, their performance notably degrades when trained on data with a long-tailed distribution. For long tail diffusion model generation, current works focus on the calibration and enhancement of the tail generation with head-tail knowledge transfer. The transfer process relies on the abundant diversity derived from the head class and, more significantly, the condition capacity of the model prediction. However, the dependency on the conditional model prediction to realize the knowledge transfer might exhibit bias during training, leading to unsatisfactory generation results and lack of robustness. Utilizing a Bayesian framework, we develop a weighted denoising score-matching technique for knowledge transfer directly from head to tail classes. Additionally, we incorporate a gating mechanism in the knowledge transfer process. We provide statistical analysis to validate this methodology, revealing that the effectiveness of such knowledge transfer depends on both label distribution and sample similarity, providing the insight to consider sample similarity when re-balancing the label proportion in training. We extensively evaluate our approach with experiments on multiple benchmark datasets, demonstrating its effectiveness and superior performance compared to existing methods. Code: \url{https://github.com/MediaBrain-SJTU/OC_LT}.

UAI Conference 2024 Conference Paper

Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models

• Xinyang Liu
• Dongsheng Wang 0003
• Bowei Fang
• Miaoge Li
• Yishi Xu
• Zhibin Duan
• Bo Chen 0001
• Mingyuan Zhou

For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts. Existing works on prompt engineering, which either require laborious manual designs or optimize the prompt tuning as a point estimation problem, may fail to describe diverse characteristics of categories and limit their applications. We introduce a Bayesian probabilistic resolution to prompt tuning, where the label-specific stochastic prompts are generated hierarchically by first sampling a latent vector from an underlying distribution and then employing a lightweight generative model. Importantly, we semantically regularize the tuning process by minimizing the statistic distance between the visual patches and linguistic prompts, which pushes the stochastic label representations to faithfully capture diverse visual concepts, instead of overfitting the training categories. We evaluate the effectiveness of our approach on four tasks: few-shot image recognition, base-to-new generalization, dataset transfer learning, and domain shifts. Extensive results on over 15 datasets show promising transferability and generalization performance of our proposed model, both quantitatively and qualitatively.

NeurIPS Conference 2024 Conference Paper

Pseudo-Private Data Guided Model Inversion Attacks

• Xiong Peng
• Bo Han
• Feng Liu
• Tongliang Liu
• Mingyuan Zhou

In model inversion attacks (MIAs), adversaries attempt to recover private training data by exploiting access to a well-trained target model. Recent advancements have improved MIA performance using a two-stage generative framework. This approach first employs a generative adversarial network to learn a fixed distributional prior, which is then used to guide the inversion process during the attack. However, in this paper, we observed a phenomenon that such a fixed prior would lead to a low probability of sampling actual private data during the inversion process due to the inherent distribution gap between the prior distribution and the private data distribution, thereby constraining attack performance. To address this limitation, we propose increasing the density around high-quality pseudo-private data—recovered samples through model inversion that exhibit characteristics of the private training data—by slightly tuning the generator. This strategy effectively increases the probability of sampling actual private data that is close to these pseudo-private data during the inversion process. After integrating our method, the generative model inversion pipeline is strengthened, leading to improvements over state-of-the-art MIAs. This paves the way for new research directions in generative MIAs.

ICML Conference 2024 Conference Paper

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation

• Mingyuan Zhou
• Huangjie Zheng
• Zhendong Wang 0005
• Mingzhang Yin
• Hai Huang

We introduce Score identity Distillation (SiD), an innovative data-free method that distills the generative capabilities of pretrained diffusion models into a single-step generator. SiD not only facilitates an exponentially fast reduction in Fréchet inception distance (FID) during distillation but also approaches or even exceeds the FID performance of the original teacher diffusion models. By reformulating forward diffusion processes as semi-implicit distributions, we leverage three score-related identities to create an innovative loss mechanism. This mechanism achieves rapid FID reduction by training the generator using its own synthesized images, eliminating the need for real data or reverse-diffusion-based generation, all accomplished within significantly shortened generation time. Upon evaluation across four benchmark datasets, the SiD algorithm demonstrates high iteration efficiency during distillation and surpasses competing distillation approaches, whether they are one-step or few-step, data-free, or dependent on training data, in terms of generation quality. This achievement not only redefines the benchmarks for efficiency and effectiveness in diffusion distillation but also in the broader field of diffusion-based generation. The PyTorch implementation is available at https: //github. com/mingyuanzhou/SiD.

ICML Conference 2024 Conference Paper

Switchable Decision: Dynamic Neural Generation Networks

• Shujian Zhang
• Korawat Tanwisuth
• Chengyue Gong
• Pengcheng He
• Mingyuan Zhou

Auto-regressive generation models achieve competitive performance across many different NLP tasks such as summarization, question answering, and classifications. However, they are also known for being slow in inference, which makes them challenging to deploy in real-time applications. We propose a switchable decision to accelerate inference by dynamically assigning computation resources for each data instance. Automatically making decisions on where to skip and how to balance quality and computation cost with constrained optimization, our dynamic neural generation networks enforce the efficient inference path and determine the optimized trade-off. Experiments across question answering, summarization, and classification benchmarks show that our method benefits from less computation cost during inference while keeping the same accuracy. Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.

ICLR Conference 2024 Conference Paper

Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting

• Yuxin Li 0003
• Wenchao Chen
• Xinyue Hu
• Bo Chen 0001
• Baolin Sun
• Mingyuan Zhou

Transformers have gained widespread usage in multivariate time series (MTS) forecasting, delivering impressive performance. Nonetheless, these existing transformer-based methods often neglect an essential aspect: the incorporation of uncertainty into the predicted series, which holds significant value in decision-making. In this paper, we introduce a Transformer-Modulated Diffusion Model (TMDM), uniting conditional diffusion generative process with transformers into a unified framework to enable precise distribution forecasting for MTS. TMDM harnesses the power of transformers to extract essential insights from historical time series data. This information is then utilized as prior knowledge, capturing covariate-dependence in both the forward and reverse processes within the diffusion model. Furthermore, we seamlessly integrate well-designed transformer-based forecasting methods into TMDM to enhance its overall performance. Additionally, we introduce two novel metrics for evaluating uncertainty estimation performance. Through extensive experiments on six datasets using four evaluation metrics, we establish the effectiveness of TMDM in probabilistic MTS forecasting.

ICML Conference 2024 Conference Paper

Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection

• Yuxin Li 0003
• Yaoxuan Feng
• Bo Chen 0001
• Wenchao Chen
• Yubiao Wang
• Xinyue Hu
• Baolin Sun
• Chunhui Qu

Multi-class unsupervised anomaly detection aims to create a unified model for identifying anomalies in objects from multiple classes when only normal data is available. In such a challenging setting, widely used reconstruction-based networks persistently grapple with the "identical shortcut" problem, wherein the infiltration of abnormal information from the condition biases the output towards an anomalous distribution. In response to this critical challenge, we introduce a Vague Prototype-Oriented Diffusion Model (VPDM) that extracts only fundamental information from the condition to prevent the occurrence of the "identical shortcut" problem from the input layer. This model leverages prototypes that contain only vague information about the target as the initial condition. Subsequently, a novel conditional diffusion model is introduced to incrementally enhance details based on vague conditions. Finally, a Vague Prototype-Oriented Optimal Transport (VPOT) method is proposed to provide more accurate information about conditions. All these components are seamlessly integrated into a unified optimization objective. The effectiveness of our approach is demonstrated across diverse datasets, including the MVTec, VisA, and MPDD benchmarks, achieving state-of-the-art results.

ICML Conference 2023 Conference Paper

Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process

• Zhibin Duan
• Xinyang Liu
• Yudi Su
• Yishi Xu
• Bo Chen 0001
• Mingyuan Zhou

Deep topic models have shown an impressive ability to extract multi-layer document latent representations and discover hierarchical semantically meaningful topics. However, most deep topic models are limited to the single-step generative process, despite the fact that the progressive generative process has achieved impressive performance in modeling image data. To this end, in this paper, we propose a novel progressive deep topic model that consists of a knowledge-informed textural data coarsening process and a corresponding progressive generative model. The former is used to build multi-level observations ranging from concrete to abstract, while the latter is used to generate more concrete observations gradually. Additionally, we incorporate a graph-enhanced decoder to capture the semantic relationships among words at different levels of observation. Furthermore, we perform a theoretical analysis of the proposed model based on the principle of information theory and show how it can alleviate the well-known "latent variable collapse" problem. Finally, extensive experiments demonstrate that our proposed model effectively improves the ability of deep topic models, resulting in higher-quality latent document representations and topics.

NeurIPS Conference 2023 Conference Paper

Beta Diffusion

• Mingyuan Zhou
• Tianqi Chen
• Zhendong Wang
• Huangjie Zheng

We introduce beta diffusion, a novel generative modeling method that integrates demasking and denoising to generate data within bounded ranges. Using scaled and shifted beta distributions, beta diffusion utilizes multiplicative transitions over time to create both forward and reverse diffusion processes, maintaining beta distributions in both the forward marginals and the reverse conditionals, given the data at any point in time. Unlike traditional diffusion-based generative models relying on additive Gaussian noise and reweighted evidence lower bounds (ELBOs), beta diffusion is multiplicative and optimized with KL-divergence upper bounds (KLUBs) derived from the convexity of the KL divergence. We demonstrate that the proposed KLUBs are more effective for optimizing beta diffusion compared to negative ELBOs, which can also be derived as the KLUBs of the same KL divergence with its two arguments swapped. The loss function of beta diffusion, expressed in terms of Bregman divergence, further supports the efficacy of KLUBs for optimization. Experimental results on both synthetic data and natural images demonstrate the unique capabilities of beta diffusion in generative modeling of range-bounded data and validate the effectiveness of KLUBs in optimizing diffusion models, thereby making them valuable additions to the family of diffusion-based generative models and the optimization techniques used to train them.

NeurIPS Conference 2023 Conference Paper

Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes

• Yishi Xu
• Jianqiao Sun
• Yudi Su
• Xinyang Liu
• Zhibin Duan
• Bo Chen
• Mingyuan Zhou

Embedding-based neural topic models have turned out to be a superior option for low-resourced topic modeling. However, current approaches consider static word embeddings learnt from source tasks as general knowledge that can be transferred directly to the target task, discounting the dynamically changing nature of word meanings in different contexts, thus typically leading to sub-optimal results when adapting to new tasks with unfamiliar contexts. To settle this issue, we provide an effective method that centers on adaptively generating semantically tailored word embeddings for each task by fully exploiting contextual information. Specifically, we first condense the contextual syntactic dependencies of words into a semantic graph for each task, which is then modeled by a Variational Graph Auto-Encoder to produce task-specific word representations. On this basis, we further impose a learnable Gaussian mixture prior on the latent space of words to efficiently learn topic representations from a clustering perspective, which contributes to diverse topic discovery and fast adaptation to novel tasks. We have conducted a wealth of quantitative and qualitative experiments, and the results show that our approach comprehensively outperforms established topic models.

TMLR Journal 2023 Journal Article

Contrastive Attraction and Contrastive Repulsion for Representation Learning

• Huangjie Zheng
• Xu Chen
• Jiangchao Yao
• Hongxia Yang
• Chunyuan Li
• Ya Zhang
• Hao Zhang
• Ivor Tsang

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By leveraging large amounts of unlabeled image data, recent CL methods have achieved promising results when pretrained on large-scale datasets, such as ImageNet. However, most of them consider the augmented views from the same instance are positive pairs, while views from other instances are negative ones. Such binary partition insufficiently considers the relation between samples and tends to yield worse performance when generalized on images in the wild. In this paper, to further improve the performance of CL and enhance its robustness on various datasets, we propose a doubly CL strategy that contrasts positive samples and negative ones within themselves separately. We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples. Theoretical analysis reveals that CACR generalizes CL's behavior by positive attraction and negative repulsion. It further considers the intra-contrastive relation within the positive and negative pairs to narrow the gap between the sampled and true distribution, which is important when datasets are less curated. Extensive large-scale experiments on standard vision tasks show that CACR not only consistently outperforms existing CL methods on benchmark datasets, but also shows better robustness when generalized on imbalanced image datasets.

ICLR Conference 2023 Conference Paper

Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning

• Zhendong Wang 0005
• Jonathan J. Hunt
• Mingyuan Zhou

Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL. Standard RL methods often perform poorly in this regime due to the function approximation errors on out-of-distribution actions. While a variety of regularization methods have been proposed to mitigate this issue, they are often constrained by policy classes with limited expressiveness that can lead to highly suboptimal solutions. In this paper, we propose representing the policy as a diffusion model, a recent class of highly-expressive deep generative models. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. In our approach, we learn an action-value function and we add a term maximizing action-values into the training loss of the conditional diffusion model, which results in a loss that seeks optimal actions that are near the behavior policy. We show the expressiveness of the diffusion model-based policy, and the coupling of the behavior cloning and policy improvement under the diffusion model both contribute to the outstanding performance of Diffusion-QL. We illustrate the superiority of our method compared to prior works in a simple 2D bandit example with a multimodal behavior policy. We then show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.

ICLR Conference 2023 Conference Paper

Diffusion-GAN: Training GANs with Diffusion

• Zhendong Wang 0005
• Huangjie Zheng
• Pengcheng He
• Weizhu Chen
• Mingyuan Zhou

Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate Gaussian-mixture distributed instance noise. Diffusion-GAN consists of three components, including an adaptive diffusion process, a diffusion timestep-dependent discriminator, and a generator. Both the observed and generated data are diffused by the adaptive diffusion process via different noise-to-data ratios at each timestep. The timestep-dependent discriminator learns to distinguish the diffused real data from the diffused generated data at each diffusion timestep. The generator learns from the discriminator's feedback by backpropagating through the forward diffusion chain, whose length is adaptively adjusted to balance the noise and data levels. We theoretically show that the discriminator's timestep-dependent strategy gives consistent and helpful guidance to the generator, enabling it to match the true data distribution. We demonstrate the advantages of Diffusion-GAN over strong GAN baselines on various datasets, showing that it can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.

ICLR Conference 2023 Conference Paper

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems

• Yihao Feng
• Shentao Yang
• Shujian Zhang
• Jianguo Zhang 0005
• Caiming Xiong
• Mingyuan Zhou
• Huan Wang 0016

When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied. This paper aims at answering the question of how to efficiently learn and leverage a reward function for training end-to-end (E2E) ToD agents. Specifically, we introduce two generalized objectives for reward-function learning, inspired by the classical learning-to-rank literature. Further, we utilize the learned reward function to guide the training of the E2E ToD agent. With the proposed techniques, we achieve competitive results on the E2E response-generation task on the Multiwoz 2.0 dataset. Source code and checkpoints are publicly released at https://github.com/Shentao-YANG/Fantastic_Reward_ICLR2023.

NeurIPS Conference 2023 Conference Paper

Few-shot Generation via Recalling Brain-Inspired Episodic-Semantic Memory

• Zhibin Duan
• Zhiyi Lv
• Chaojie Wang
• Bo Chen
• Bo An
• Mingyuan Zhou

Aimed at adapting a generative model to a novel generation task with only a few given data samples, the capability of few-shot generation is crucial for many real-world applications with limited data, \emph{e. g. }, artistic domains. Instead of training from scratch, recent works tend to leverage the prior knowledge stored in previous datasets, which is quite similar to the memory mechanism of human intelligence, but few of these works directly imitate the memory-recall mechanism that humans make good use of in accomplishing creative tasks, \emph{e. g. }, painting and writing. Inspired by the memory mechanism of human brain, in this work, we carefully design a variational structured memory module (VSM), which can simultaneously store both episodic and semantic memories to assist existing generative models efficiently recall these memories during sample generation. Meanwhile, we introduce a bionic memory updating strategy for the conversion between episodic and semantic memories, which can also model the uncertainty during conversion. Then, we combine the developed VSM with various generative models under the Bayesian framework, and evaluate these memory-augmented generative models with few-shot generation tasks, demonstrating the effectiveness of our methods.

NeurIPS Conference 2023 Conference Paper

In-Context Learning Unlocked for Diffusion Models

• Zhendong Wang
• Yifan Jiang
• Yadong Lu
• Yelong Shen
• Pengcheng He
• Weizhu Chen
• Zhangyang "Atlas" Wang
• Mingyuan Zhou

We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our model automatically understands the underlying task and performs the same task on a new query image following the text guidance. To achieve this, we propose a vision-language prompt that can model a wide range of vision-language tasks and a diffusion model that takes it as input. The diffusion model is trained jointly on six different tasks using these prompts. The resulting Prompt Diffusion model becomes the first diffusion-based vision-language foundation model capable of in-context learning. It demonstrates high-quality in-context generation for the trained tasks and effectively generalizes to new, unseen vision tasks using their respective prompts. Our model also shows compelling text-guided image editing results. Our framework aims to facilitate research into in-context learning for computer vision. We share our code and pre-trained models at https: //github. com/Zhendong-Wang/Prompt-Diffusion.

ICML Conference 2023 Conference Paper

Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling

• Tianqi Chen
• Mingyuan Zhou

Learning to denoise has emerged as a prominent paradigm to design state-of-the-art deep generative models for natural images. How to use it to model the distributions of both continuous real-valued data and categorical data has been well studied in recently proposed diffusion models. However, it is found in this paper to have limited ability in modeling some other types of data, such as count and non-negative continuous data, that are often highly sparse, skewed, heavy-tailed, and/or overdispersed. To this end, we propose learning to jump as a general recipe for generative modeling of various types of data. Using a forward count thinning process to construct learning objectives to train a deep neural network, it employs a reverse count thickening process to iteratively refine its generation through that network. We demonstrate when learning to jump is expected to perform comparably to learning to denoise, and when it is expected to perform better. For example, learning to jump is recommended when the training data is non-negative and exhibits strong sparsity, skewness, heavy-tailedness, and/or heterogeneity.

NeurIPS Conference 2023 Conference Paper

Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models

• Zhendong Wang
• Yifan Jiang
• Huangjie Zheng
• Peihao Wang
• Pengcheng He
• Zhangyang "Atlas" Wang
• Weizhu Chen
• Mingyuan Zhou

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which thus helps democratize diffusion model training to broader users. At the core of our innovations is a new conditional score function at the patch level, where the patch location in the original image is included as additional coordinate channels, while the patch size is randomized and diversified throughout training to encode the cross-region dependency at multiple scales. Sampling with our method is as easy as in the original diffusion model. Through Patch Diffusion, we could achieve $\mathbf{\ge 2\times}$ faster training, while maintaining comparable or better generation quality. Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e. g. $, as few as 5, 000 images to train from scratch. We achieve outstanding FID scores in line with state-of-the-art benchmarks: 1. 77 on CelebA-64$\times$64, 1. 93 on AFHQv2-Wild-64$\times$64, and 2. 72 on ImageNet-256$\times$256. We share our code and pre-trained models at https: //github. com/Zhendong-Wang/Patch-Diffusion.

ICML Conference 2023 Conference Paper

POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models

• Korawat Tanwisuth
• Shujian Zhang
• Huangjie Zheng
• Pengcheng He
• Mingyuan Zhou

Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to adapt them to downstream tasks. To overcome this critical limitation, we propose an unsupervised fine-tuning framework to directly fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models, by aligning the discrete distributions extracted from the prompts and target data. To verify our approach’s applicability, we conduct extensive experiments on image classification, sentiment analysis, and natural language inference tasks. Across 13 image-related tasks and 15 language-related ones, the proposed approach achieves consistent improvements over the baselines. PyTorch code is available at https: //github. com/korawat-tanwisuth/POUF.

NeurIPS Conference 2023 Conference Paper

Preference-grounded Token-level Guidance for Language Model Fine-tuning

• Shentao Yang
• Shujian Zhang
• Congying Xia
• Yihao Feng
• Caiming Xiong
• Mingyuan Zhou

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the token level. There is, therefore, a granularity mismatch between the preference and the LM training losses, which may complicate the learning problem. In this paper, we address this issue by developing an alternate training process, where we iterate between grounding the sequence-level preference into token-level training guidance, and improving the LM with the learned guidance. For guidance learning, we design a framework that extends the pairwise-preference learning in imitation learning to both variable-length LM generation and the utilization of the preference among multiple generations. For LM training, based on the amount of supervised data, we present two minimalist learning objectives that utilize the learned guidance. In experiments, our method performs competitively on two distinct representative LM tasks --- discrete-prompt generation and text summarization.

ICML Conference 2023 Conference Paper

Prototype-oriented unsupervised anomaly detection for multivariate time series

• Yuxin Li 0003
• Wenchao Chen
• Bo Chen 0001
• Dongsheng Wang 0003
• Long Tian
• Mingyuan Zhou

Unsupervised anomaly detection (UAD) of multivariate time series (MTS) aims to learn robust representations of normal multivariate temporal patterns. Existing UAD methods try to learn a fixed set of mappings for each MTS, entailing expensive computation and limited model adaptation. To address this pivotal issue, we propose a prototype-oriented UAD (PUAD) method under a probabilistic framework. Specifically, instead of learning the mappings for each MTS, the proposed PUAD views multiple MTSs as the distribution over a group of prototypes, which are extracted to represent a diverse set of normal patterns. To learn and regulate the prototypes, PUAD introduces a reconstruction-based unsupervised anomaly detection approach, which incorporates a prototype-oriented optimal transport method into a Transformer-powered probabilistic dynamical generative framework. Leveraging meta-learned transferable prototypes, PUAD can achieve high model adaptation capacity for new MTSs. Experiments on five public MTS datasets all verify the effectiveness of the proposed UAD method.

ICLR Conference 2023 Conference Paper

Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders

• Huangjie Zheng
• Pengcheng He
• Weizhu Chen
• Mingyuan Zhou

Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly because it needs many forward and reverse steps. We propose a faster and cheaper approach that adds noise not until the data become pure random noise, but until they reach a hidden noisy data distribution that we can confidently learn. Then, we use fewer reverse steps to generate data by starting from this hidden distribution that is made similar to the noisy data. We reveal that the proposed model can be cast as an adversarial auto-encoder empowered by both the diffusion process and a learnable implicit prior. Experimental results show even with a significantly smaller number of reverse diffusion steps, the proposed truncated diffusion probabilistic models can provide consistent improvements over the non-truncated ones in terms of performance in both unconditional and text-guided image generations.

JMLR Journal 2023 Journal Article

Weibull Racing Survival Analysis with Competing Events, Left Truncation, and Time-Varying Covariates

• Quan Zhang
• Yanxun Xu
• Mei-Cheng Wang
• Mingyuan Zhou

We propose Bayesian nonparametric Weibull delegate racing (WDR) to fill the gap in interpretable nonlinear survival analysis with competing events, left truncation, and time-varying covariates. We set a two-phase race among a potentially infinite number of sub-events to model nonlinear covariate effects, which does not rely on transformations or complex functions of the covariates. Using gamma processes, the nonlinear capacity of WDR is parsimonious and data-adaptive. In prediction accuracy, WDR dominates cause-specific Cox and Fine-Gray models and is comparable to random survival forests in the presence of time-invariant covariates. More importantly, WDR can cope with different types of censoring, missing outcomes, left truncation, and time-varying covariates, on which other nonlinear models, such as the random survival forests, Gaussian processes, and deep learning approaches, are largely silent. We develop an efficient MCMC algorithm based on Gibbs sampling. We analyze biomedical data, interpret disease progression affected by covariates, and show the potential of WDR in discovering and diagnosing new diseases. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

NeurIPS Conference 2022 Conference Paper

A Unified Framework for Alternating Offline Model Training and Policy Learning

• Shentao Yang
• Shujian Zhang
• Yihao Feng
• Mingyuan Zhou

In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the environment. Offline MBRL algorithms can improve the efficiency and stability of policy learning over the model-free algorithms. However, in most of the existing offline MBRL algorithms, the learning objectives for the dynamic models and the policies are isolated from each other. Such an objective mismatch may lead to inferior performance of the learned agents. In this paper, we address this issue by developing an iterative offline MBRL framework, where we maximize a lower bound of the true expected return, by alternating between dynamic-model training and policy learning. With the proposed unified model-policy learning framework, we achieve competitive performance on a wide range of continuous-control offline reinforcement learning datasets. Source code is released at https: //github. com/Shentao-YANG/AMPL_NeurIPS2022.

NeurIPS Conference 2022 Conference Paper

A Variational Edge Partition Model for Supervised Graph Representation Learning

• Yilin He
• Chaojie Wang
• Hao Zhang
• Bo Chen
• Mingyuan Zhou

Graph neural networks (GNNs), which propagate the node features through the edges and learn how to transform the aggregated features under label supervision, have achieved great success in supervised feature extraction for both node-level and graph-level classification tasks. However, GNNs typically treat the graph structure as given and ignore how the edges are formed. This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities, each of which contributes to the edges via a logical OR mechanism. Based on this generative model, we partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN-based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN-based predictor that combines community-specific GNNs for the end classification task. Extensive evaluations on real-world graph datasets have verified the effectiveness of the proposed method in learning discriminative representations for both node-level and graph-level classification tasks.

NeurIPS Conference 2022 Conference Paper

Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport

• DanDan Guo
• Long Tian
• He Zhao
• Mingyuan Zhou
• Hongyuan Zha

Few-shot classification aims to learn a classifier to recognize unseen classes during training, where the learned model can easily become over-fitted based on the biased distribution formed by only a few training examples. A recent solution to this problem is calibrating the distribution of these few sample classes by transferring statistics from the base classes with sufficient examples, where how to decide the transfer weights from base classes to novel classes is the key. However, principled approaches for learning the transfer weights have not been carefully studied. To this end, we propose a novel distribution calibration method by learning the adaptive weight matrix between novel samples and base classes, which is built upon a hierarchical Optimal Transport (H-OT) framework. By minimizing the high-level OT distance between novel samples and base classes, we can view the learned transport plan as the adaptive weight information for transferring the statistics of base classes. The learning of the cost function between a base class and novel class in the high-level OT leads to the introduction of the low-level OT, which considers the weights of all the data samples in the base class. Experimental results on standard benchmarks demonstrate that our proposed plug-and-play model outperforms competing approaches and owns desired cross-domain generalization ability, indicating the effectiveness of the learned adaptive weights.

NeurIPS Conference 2022 Conference Paper

Alleviating "Posterior Collapse'' in Deep Topic Models via Policy Gradient

• Yewen Li
• Chaojie Wang
• Zhibin Duan
• Dongsheng Wang
• Bo Chen
• Bo An
• Mingyuan Zhou

Deep topic models have been proven as a promising way to extract hierarchical latent representations from documents represented as high-dimensional bag-of-words vectors. However, the representation capability of existing deep topic models is still limited by the phenomenon of "posterior collapse", which has been widely criticized in deep generative models, resulting in the higher-level latent representations exhibiting similar or meaningless patterns. To this end, in this paper, we first develop a novel deep-coupling generative process for existing deep topic models, which incorporates skip connections into the generation of documents, enforcing strong links between the document and its multi-layer latent representations. After that, utilizing data augmentation techniques, we reformulate the deep-coupling generative process as a Markov decision process and develop a corresponding Policy Gradient (PG) based training algorithm, which can further alleviate the information reduction at higher layers. Extensive experiments demonstrate that our developed methods can effectively alleviate "posterior collapse" in deep topic models, contributing to providing higher-quality latent document representations.

ICML Conference 2022 Conference Paper

Bayesian Deep Embedding Topic Meta-Learner

• Zhibin Duan
• Yishi Xu
• Jianqiao Sun
• Bo Chen 0001
• Wenchao Chen
• Chaojie Wang 0001
• Mingyuan Zhou

Existing deep topic models are effective in capturing the latent semantic structures in textual data but usually rely on a plethora of documents. This is less than satisfactory in practical applications when only a limited amount of data is available. In this paper, we propose a novel framework that efficiently solves the problem of topic modeling under the small data regime. Specifically, the framework involves two innovations: a bi-level generative model that aims to exploit the task information to guide the document generation, and a topic meta-learner that strives to learn a group of global topic embeddings so that fast adaptation to the task-specific topic embeddings can be achieved with a few examples. We apply the proposed framework to a hierarchical embedded topic model and achieve better performance than various baseline models on diverse experiments, including few-shot topic discovery and few-shot document classification.

NeurIPS Conference 2022 Conference Paper

CARD: Classification and Regression Diffusion Models

• Xizewen Han
• Huangjie Zheng
• Mingyuan Zhou

Learning the distribution of a continuous or categorical response variable y given its covariates x is a fundamental problem in statistics and machine learning. Deep neural network-based supervised learning algorithms have made great progress in predicting the mean of y given x, but they are often criticized for their ability to accurately capture the uncertainty of their predictions. In this paper, we introduce classification and regression diffusion (CARD) models, which combine a denoising diffusion-based conditional generative model and a pre-trained conditional mean estimator, to accurately predict the distribution of y given x. We demonstrate the outstanding ability of CARD in conditional distribution prediction with both toy examples and real-world datasets, the experimental results on which show that CARD, in general, outperforms state-of-the-art methods, including Bayesian neural network-based one, designed for uncertainty estimation, especially when the conditional distribution of y given x is multi-modal. In addition, we utilize the stochastic nature of the generative model outputs to obtain a finer granularity in model confidence assessment at the instance level for classification tasks.

ICML Conference 2022 Conference Paper

Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection

• Wenchao Chen
• Long Tian
• Bo Chen 0001
• Liang Dai
• Zhibin Duan
• Mingyuan Zhou

Anomaly detection within multivariate time series (MTS) is an essential task in both data mining and service quality management. Many recent works on anomaly detection focus on designing unsupervised probabilistic models to extract robust normal patterns of MTS. In this paper, we model sensor dependency and stochasticity within MTS by developing an embedding-guided probabilistic generative network. We combine it with adaptive variational graph convolutional recurrent network %and get variational GCRN (VGCRN) to model both spatial and temporal fine-grained correlations in MTS. To explore hierarchical latent representations, we further extend VGCRN into a deep variational network, which captures multilevel information at different layers and is robust to noisy time series. Moreover, we develop an upward-downward variational inference scheme that considers both forecasting-based and reconstruction-based losses, achieving an accurate posterior approximation of latent variables with better MTS representations. The experiments verify the superiority of the proposed method over current state-of-the-art methods.

NeurIPS Conference 2022 Conference Paper

HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding

• Yi. shi Xu
• Dongsheng Wang
• Bo Chen
• Ruiying Lu
• Zhibin Duan
• Mingyuan Zhou

Embedded topic models are able to learn interpretable topics even with large and heavy-tailed vocabularies. However, they generally hold the Euclidean embedding space assumption, leading to a basic limitation in capturing hierarchical relations. To this end, we present a novel framework that introduces hyperbolic embeddings to represent words and topics. With the tree-likeness property of hyperbolic space, the underlying semantic hierarchy among words and topics can be better exploited to mine more interpretable topics. Furthermore, due to the superiority of hyperbolic geometry in representing hierarchical data, tree-structure knowledge can also be naturally injected to guide the learning of a topic hierarchy. Therefore, we further develop a regularization term based on the idea of contrastive learning to inject prior structural knowledge efficiently. Experiments on both topic taxonomy discovery and document representation demonstrate that the proposed framework achieves improved performance against existing embedded topic models.

NeurIPS Conference 2022 Conference Paper

Knowledge-Aware Bayesian Deep Topic Model

• Dongsheng Wang
• Yi. shi Xu
• Miaoge Li
• Zhibin Duan
• Chaojie Wang
• Bo Chen
• Mingyuan Zhou

We propose a Bayesian generative model for incorporating prior domain knowledge into hierarchical topic modeling. Although embedded topic models (ETMs) and its variants have gained promising performance in text analysis, they mainly focus on mining word co-occurrence patterns, ignoring potentially easy-to-obtain prior topic hierarchies that could help enhance topic coherence. While several knowledge-based topic models have recently been proposed, they are either only applicable to shallow hierarchies or sensitive to the quality of the provided prior knowledge. To this end, we develop a novel deep ETM that jointly models the documents and the given prior knowledge by embedding the words and topics into the same space. Guided by the provided domain knowledge, the proposed model tends to discover topic hierarchies that are organized into interpretable taxonomies. Moreover, with a technique for adapting a given graph, our extended version allows the structure of the prior knowledge to be fine-tuned to match the target corpus. Extensive experiments show that our proposed model efficiently integrates the prior knowledge and improves both hierarchical topic discovery and document representation.

ICLR Conference 2022 Conference Paper

Learning Prototype-oriented Set Representations for Meta-Learning

• Dandan Guo
• Long Tian
• Minghe Zhang
• Mingyuan Zhou
• Hongyuan Zha

Learning from set-structured data is a fundamental problem that has recently attracted increasing attention, where a series of summary networks are introduced to deal with the set input. In fact, many meta-learning problems can be treated as set-input tasks. Most existing summary networks aim to design different architectures for the input set in order to enforce permutation invariance. However, scant attention has been paid to the common cases where different sets in a meta distribution are closely related and share certain statistical properties. Viewing each set as a distribution over a set of global prototypes, this paper provides a novel prototype-oriented optimal transport (POT) framework to improve existing summary networks. To learn the distribution over the global prototypes, we minimize its regularized optimal transport distance to the set empirical distribution over data points, providing a natural unsupervised way to improve the summary network. Since our plug-and-play framework can be applied to many meta learning problems, we further instantiate it to the cases of few-shot classification and implicit meta generative modeling. Extensive experiments demonstrate that our framework significantly improves the existing summary networks on learning more powerful summary statistics from sets and can be successfully integrated into metric-based few-shot classification and generative modeling applications, providing a promising tool for addressing set-input and meta-learning problems.

NeurIPS Conference 2022 Conference Paper

Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification

• DanDan Guo
• Zhuo Li
• meixi zheng
• He Zhao
• Mingyuan Zhou
• Hongyuan Zha

Imbalanced data pose challenges for deep learning based classification models. One of the most widely-used approaches for tackling imbalanced data is re-weighting, where training samples are associated with different weights in the loss function. Most of existing re-weighting approaches treat the example weights as the learnable parameter and optimize the weights on the meta set, entailing expensive bilevel optimization. In this paper, we propose a novel re-weighting method based on optimal transport (OT) from a distributional point of view. Specifically, we view the training set as an imbalanced distribution over its samples, which is transported by OT to a balanced distribution obtained from the meta set. The weights of the training samples are the probability mass of the imbalanced distribution andlearned by minimizing the OT distance between the two distributions. Compared with existing methods, our proposed one disengages the dependence of the weight learning on the concerned classifier at each iteration. Experiments on image, text and point cloud datasets demonstrate that our proposed re-weighting method has excellent performance, achieving state-of-the-art results in many cases andproviding a promising tool for addressing the imbalanced classification issue. The code has been made available athttps: //github. com/DandanGuo1993/reweight-imbalance-classification-with-OT.

ICLR Conference 2022 Conference Paper

Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

• Haoang Chi
• Feng Liu 0003
• Wenjing Yang 0002
• Long Lan
• Tongliang Liu
• Bo Han 0003
• Gang Niu 0001
• Mingyuan Zhou

In novel class discovery (NCD), we are given labeled data from seen classes and unlabeled data from unseen classes, and we train clustering models for the unseen classes. However, the implicit assumptions behind NCD are still unclear. In this paper, we demystify assumptions behind NCD and find that high-level semantic features should be shared among the seen and unseen classes. Based on this finding, NCD is theoretically solvable under certain assumptions and can be naturally linked to meta-learning that has exactly the same assumption as NCD. Thus, we can empirically solve the NCD problem by meta-learning algorithms after slight modifications. This meta-learning-based methodology significantly reduces the amount of unlabeled data needed for training and makes it more practical, as demonstrated in experiments. The use of very limited data is also justified by the application scenario of NCD: since it is unnatural to label only seen-class data, NCD is sampling instead of labeling in causality. Therefore, unseen-class data should be collected on the way of collecting seen-class data, which is why they are novel and first need to be clustered.

ICML Conference 2022 Conference Paper

Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning

• Shentao Yang
• Yihao Feng
• Shujian Zhang
• Mingyuan Zhou

Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is the instability of policy training, caused by the mismatch between the distribution of the offline data and the undiscounted stationary state-action distribution of the learned policy. To avoid the detrimental impact of distribution mismatch, we regularize the undiscounted stationary distribution of the current policy towards the offline data during the policy optimization process. Further, we train a dynamics model to both implement this regularization and better estimate the stationary distribution of the current policy, reducing the error induced by distribution mismatch. On a wide range of continuous-control offline RL datasets, our method indicates competitive performance, which validates our algorithm. The code is publicly available.

ICLR Conference 2022 Conference Paper

Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings

• Dongsheng Wang 0003
• Dandan Guo
• He Zhao 0001
• Huangjie Zheng
• Korawat Tanwisuth
• Bo Chen 0001
• Mingyuan Zhou

A topic model is often formulated as a generative model that explains how each word of a document is generated given a set of topics and document-specific topic proportions. It is focused on capturing the word co-occurrences in a document and hence often suffers from poor performance in analyzing short documents. In addition, its parameter estimation often relies on approximate posterior inference that is either not scalable or suffering from large approximation error. This paper introduces a new topic-modeling framework where each document is viewed as a set of word embedding vectors and each topic is modeled as an embedding vector in the same embedding space. Embedding the words and topics in the same vector space, we define a method to measure the semantic difference between the embedding vectors of the words of a document and these of the topics, and optimize the topic embeddings to minimize the expected difference over all documents. Experiments on text analysis demonstrate that the proposed method, which is amenable to mini-batch stochastic gradient descent based optimization and hence scalable to big corpora, provides competitive performance in discovering more coherent and diverse topics and extracting better document representations.

NeurIPS Conference 2021 Conference Paper

A Prototype-Oriented Framework for Unsupervised Domain Adaptation

• Korawat Tanwisuth
• Xinjie Fan
• Huangjie Zheng
• Shujian Zhang
• Hao Zhang
• Bo Chen
• Mingyuan Zhou

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns that often plague these methods, we instead provide a memory and computation-efficient probabilistic framework to extract class prototypes and align the target features with them. We demonstrate the general applicability of our method on a wide range of scenarios, including single-source, multi-source, class-imbalance, and source-private domain adaptation. Requiring no additional model parameters and having a moderate increase in computation over the source model alone, the proposed method achieves competitive performance with state-of-the-art methods.

NeurIPS Conference 2021 Conference Paper

Alignment Attention by Matching Key and Query Distributions

• Shujian Zhang
• Xinjie Fan
• Huangjie Zheng
• Korawat Tanwisuth
• Mingyuan Zhou

The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains. Most such models use multi-head self-attention which is appealing for the ability to attend to information from different perspectives. This paper introduces alignment attention that explicitly encourages self-attention to match the distributions of the key and query within each head. The resulting alignment attention networks can be optimized as an unsupervised regularization in the existing attention framework. It is simple to convert any models with self-attention, including pre-trained ones, to the proposed alignment attention. On a variety of language understanding tasks, we show the effectiveness of our method in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks. We further demonstrate the general applicability of our approach on graph attention and visual question answering, showing the great potential of incorporating our alignment method into various attention-related tasks.

ICML Conference 2021 Conference Paper

ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables

• Aleksandar Dimitriev
• Mingyuan Zhou

Estimating the gradients for binary variables is a task that arises frequently in various domains, such as training discrete latent variable models. What has been commonly used is a REINFORCE based Monte Carlo estimation method that uses either independent samples or pairs of negatively correlated samples. To better utilize more than two samples, we propose ARMS, an Antithetic REINFORCE-based Multi-Sample gradient estimator. ARMS uses a copula to generate any number of mutually antithetic samples. It is unbiased, has low variance, and generalizes both DisARM, which we show to be ARMS with two samples, and the leave-one-out REINFORCE (LOORF) estimator, which is ARMS with uncorrelated samples. We evaluate ARMS on several datasets for training generative models, and our experimental results show that it outperforms competing methods. We also develop a version of ARMS for optimizing the multi-sample variational bound, and show that it outperforms both VIMCO and DisARM. The code is publicly available.

ICML Conference 2021 Conference Paper

Bayesian Attention Belief Networks

• Shujian Zhang
• Xinjie Fan
• Bo Chen 0001
• Mingyuan Zhou

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated model design. This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights with a hierarchy of gamma distributions, and an encoder network by stacking Weibull distributions with a deterministic-upward-stochastic-downward structure to approximate the posterior. The resulting auto-encoding networks can be optimized in a differentiable way with a variational lower bound. It is simple to convert any models with deterministic attention, including pretrained ones, to the proposed Bayesian attention belief networks. On a variety of language understanding tasks, we show that our method outperforms deterministic attention and state-of-the-art stochastic attention in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks. We further demonstrate the general applicability of our method on neural machine translation and visual question answering, showing great potential of incorporating our method into various attention-related tasks.

NeurIPS Conference 2021 Conference Paper

CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator

• Alek Dimitriev
• Mingyuan Zhou

Accurately backpropagating the gradient through categorical variables is a challenging task that arises in various domains, such as training discrete latent variable models. To this end, we propose CARMS, an unbiased estimator for categorical random variables based on multiple mutually negatively correlated (jointly antithetic) samples. CARMS combines REINFORCE with copula based sampling to avoid duplicate samples and reduce its variance, while keeping the estimator unbiased using importance sampling. It generalizes both the ARMS antithetic estimator for binary variables, which is CARMS for two categories, as well as LOORF/VarGrad, the leave-one-out REINFORCE estimator, which is CARMS with independent samples. We evaluate CARMS on several benchmark datasets on a generative modeling task, as well as a structured output prediction task, and find it to outperform competing methods including a strong self-control baseline. The code is publicly available.

ICLR Conference 2021 Conference Paper

Contextual Dropout: An Efficient Sample-Dependent Dropout Module

• Xinjie Fan
• Shujian Zhang
• Korawat Tanwisuth
• Xiaoning Qian
• Mingyuan Zhou

Dropout has been demonstrated as a simple and effective module to not only regularize the training process of deep neural networks, but also provide the uncertainty estimation for prediction. However, the quality of uncertainty estimation is highly dependent on the dropout probabilities. Most current models use the same dropout distributions across all data samples due to its simplicity. Despite the potential gains in the flexibility of modeling uncertainty, sample-dependent dropout, on the other hand, is less explored as it often encounters scalability issues or involves non-trivial model changes. In this paper, we propose contextual dropout with an efficient structural design as a simple and scalable sample-dependent dropout module, which can be applied to a wide range of models at the expense of only slightly increased memory and computational cost. We learn the dropout probabilities with a variational objective, compatible with both Bernoulli dropout and Gaussian dropout. We apply the contextual dropout module to various models with applications to image classification and visual question answering and demonstrate the scalability of the method with large-scale datasets, such as ImageNet and VQA 2.0. Our experimental results show that the proposed method outperforms baseline methods in terms of both accuracy and quality of uncertainty estimation.

NeurIPS Conference 2021 Conference Paper

Convex Polytope Trees

• Mohammadreza Armandpour
• Ali Sadeghian
• Mingyuan Zhou

A decision tree is commonly restricted to use a single hyperplane to split the covariate space at each of its internal nodes. It often requires a large number of nodes to achieve high accuracy. In this paper, we propose convex polytope trees (CPT) to expand the family of decision trees by an interpretable generalization of their decision boundary. The splitting function at each node of CPT is based on the logical disjunction of a community of differently weighted probabilistic linear decision-makers, which also geometrically corresponds to a convex polytope in the covariate space. We use a nonparametric Bayesian prior at each node to infer the community's size, encouraging simpler decision boundaries by shrinking the number of polytope facets. We develop a greedy method to efficiently construct CPT and scalable end-to-end training algorithms for the tree parameters when the tree structure is given. We empirically demonstrate the efficiency of CPT over existing state-of-the-art decision trees in several real-world classification and regression tasks from diverse domains.

NeurIPS Conference 2021 Conference Paper

Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions

• Huangjie Zheng
• Mingyuan Zhou

To measure the difference between two probability distributions, referred to as the source and target, respectively, we exploit both the chain rule and Bayes' theorem to construct conditional transport (CT), which is constituted by both a forward component and a backward one. The forward CT is the expected cost of moving a source data point to a target one, with their joint distribution defined by the product of the source probability density function (PDF) and a source-dependent conditional distribution, which is related to the target PDF via Bayes' theorem. The backward CT is defined by reversing the direction. The CT cost can be approximated by replacing the source and target PDFs with their discrete empirical distributions supported on mini-batches, making it amenable to implicit distributions and stochastic gradient descent-based optimization. When applied to train a generative model, CT is shown to strike a good balance between mode-covering and mode-seeking behaviors and strongly resist mode collapse. On a wide variety of benchmark datasets for generative modeling, substituting the default statistical distance of an existing generative adversarial network with CT is shown to consistently improve the performance. PyTorch code is provided.

NeurIPS Conference 2021 Conference Paper

Probabilistic Margins for Instance Reweighting in Adversarial Training

• Qizhou Wang
• Feng Liu
• Bo Han
• Tongliang Liu
• Chen Gong
• Gang Niu
• Mingyuan Zhou
• Masashi Sugiyama

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However, existing methods measuring the closeness are not very reliable: they are discrete and can take only a few values, and they are path-dependent, i. e. , they may change given the same start and end points with different attack paths. In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighing adversarial data. Specifically, a PM is defined as the difference between two estimated class-posterior probabilities, e. g. , such a probability of the true label minus the probability of the most confusing label given some natural data. Though different PMs capture different geometric properties, all three PMs share a negative correlation with the vulnerability of data: data with larger/smaller PMs are safer/riskier and should have smaller/larger weights. Experiments demonstrated that PMs are reliable and PM-based reweighting methods outperformed state-of-the-art counterparts.

ICML Conference 2021 Conference Paper

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network

• Zhibin Duan
• Dongsheng Wang 0003
• Bo Chen 0001
• Chaojie Wang 0001
• Wenchao Chen
• Yewen Li
• Jie Ren
• Mingyuan Zhou

Hierarchical topic models such as the gamma belief network (GBN) have delivered promising results in mining multi-layer document representations and discovering interpretable topic taxonomies. However, they often assume in the prior that the topics at each layer are independently drawn from the Dirichlet distribution, ignoring the dependencies between the topics both at the same layer and across different layers. To relax this assumption, we propose sawtooth factorial topic embedding guided GBN, a deep generative model of documents that captures the dependencies and semantic similarities between the topics in the embedding space. Specifically, both the words and topics are represented as embedding vectors of the same dimension. The topic matrix at a layer is factorized into the product of a factor loading matrix and a topic embedding matrix, the transpose of which is set as the factor loading matrix of the layer above. Repeating this particular type of factorization, which shares components between adjacent layers, leads to a structure referred to as sawtooth factorization. An auto-encoding variational inference network is constructed to optimize the model parameter via stochastic gradient descent. Experiments on big corpora show that our models outperform other neural topic models on extracting deeper interpretable topics and deriving better document representations.

NeurIPS Conference 2021 Conference Paper

TopicNet: Semantic Graph-Guided Topic Discovery

• Zhibin Duan
• Yi. shi Xu
• Bo Chen
• Dongsheng Wang
• Chaojie Wang
• Mingyuan Zhou

Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy. However, it is unclear how to incorporate prior belief such as knowledge graph to guide the learning of the topic hierarchy. To address this issue, we introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as inductive bias to influence the learning. TopicNet represents each topic as a Gaussian-distributed embedding vector, projects the topics of all layers into a shared embedding space, and explores both the symmetric and asymmetric similarities between Gaussian embedding vectors to incorporate prior semantic hierarchies. With a variational auto-encoding inference network, the model parameters are optimized by minimizing the evidence lower bound and supervised loss via stochastic gradient descent. Experiments on widely used benchmark show that TopicNet outperforms related deep topic models on discovering deeper interpretable topics and mining better document representations.

ICLR Conference 2020 Conference Paper

Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation

• Xinjie Fan
• Yizhe Zhang 0002
• Zhendong Wang 0005
• Mingyuan Zhou

Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to contextual generation of categorical sequences a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control. Due to the correlation, the number of unique rollouts is random and adaptive to model uncertainty; those rollouts naturally become baselines for each other, and hence are combined to effectively reduce gradient variance. We also demonstrate the use of correlated MC rollouts for binary-tree softmax models, which reduce the high generation cost in large vocabulary scenarios by decomposing each categorical action into a sequence of binary actions. We evaluate our methods on both neural program synthesis and image captioning. The proposed methods yield lower gradient variance and consistent improvement over related baselines.

NeurIPS Conference 2020 Conference Paper

Bayesian Attention Modules

• Xinjie Fan
• Shujian Zhang
• Bo Chen
• Mingyuan Zhou

Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability. Most current models use deterministic attention modules due to their simplicity and ease of optimization. Stochastic counterparts, on the other hand, are less popular despite their potential benefits. The main reason is that stochastic attention often introduces optimization issues or requires significant model changes. In this paper, we propose a scalable stochastic version of attention that is easy to implement and optimize. We construct simplex-constrained attention distributions by normalizing reparameterizable distributions, making the training process differentiable. We learn their parameters in a Bayesian framework where a data-dependent prior is introduced for regularization. We apply the proposed stochastic attention modules to various attention-based models, with applications to graph node classification, visual question answering, image captioning, machine translation, and language understanding. Our experiments show the proposed method brings consistent improvements over the corresponding baselines.

ICML Conference 2020 Conference Paper

Bayesian Graph Neural Networks with Adaptive Connection Sampling

• Arman Hasanzadeh
• Ehsan Hajiramezanali
• Shahin Boluki
• Mingyuan Zhou
• Nick G. Duffield
• Krishna Narayanan 0001
• Xiaoning Qian

We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs. The proposed framework not only alleviates over-smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs. Instead of using fixed sampling rates or hand-tuning themas model hyperparameters in existing stochastic regularization methods, our adaptive connection sampling can be trained jointly with GNN model parameters in both global and local fashions. GNN training with adaptive connection sampling is shown to be mathematically equivalent to an efficient approximation of training BayesianGNNs. Experimental results with ablation studies on benchmark datasets validate that adaptively learning the sampling rate given graph training data is the key to boost the performance of GNNs in semi-supervised node classification, less prone to over-smoothing and over-fitting with more robust prediction.

NeurIPS Conference 2020 Conference Paper

Bidirectional Convolutional Poisson Gamma Dynamical Systems

• Wenchao Chen
• Chaojie Wang
• Bo Chen
• Yicheng Liu
• Hao Zhang
• Mingyuan Zhou

Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions. With word-level convolutions capturing phrase-level topics and sentence-level transitions capturing how the topic usages evolve over consecutive sentences, we aggregate the topic proportions of all sentences of a document as its feature representation. To consider not only forward but also backward sentence-level information transmissions, we further develop a bidirectional convolutional PGDS to incorporate the full contextual information to represent each sentence. For efficient inference, we construct a convolutional-recurrent inference network, which provides both sentence-level and document-level representations, and introduce a hybrid Bayesian inference scheme combining stochastic-gradient MCMC and amortized variational inference. Experimental results on a variety of document corpora demonstrate that the proposed models can extract expressive multi-level latent representations, including interpretable phrase-level topics and sentence-level temporal transitions as well as discriminative document-level features, achieving state-of-the-art document categorization performance while being memory and computation efficient.

NeurIPS Conference 2020 Conference Paper

Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network

• Chaojie Wang
• Hao Zhang
• Bo Chen
• Dongsheng Wang
• Zhengjue Wang
• Mingyuan Zhou

To analyze a collection of interconnected documents, relational topic models (RTMs) have been developed to describe both the link structure and document content, exploring their underlying relationships via a single-layer latent representation with limited expressive capability. To better utilize the document network, we first propose graph Poisson factor analysis (GPFA) that constructs a probabilistic model for interconnected documents and also provides closed-form Gibbs sampling update equations, moving beyond sophisticated approximate assumptions of existing RTMs. Extending GPFA, we develop a novel hierarchical RTM named graph Poisson gamma belief network (GPGBN), and further introduce two different Weibull distribution based variational graph auto-encoders for efficient model inference and effective network information aggregation. Experimental results demonstrate that our models extract high-quality hierarchical latent document representations, leading to improved performance over baselines on various graph analytic tasks.

NeurIPS Conference 2020 Conference Paper

Implicit Distributional Reinforcement Learning

• Yuguang Yue
• Zhendong Wang
• Mingyuan Zhou

To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution. We adopt a distributional perspective on the discounted cumulative return and model it with a state-action-dependent implicit distribution, which is approximated by the DGNs that take state-action pairs and random noises as their input. Moreover, we use the SIA to provide a semi-implicit policy distribution, which mixes the policy parameters with a reparameterizable distribution that is not constrained by an analytic density function. In this way, the policy's marginal distribution is implicit, providing the potential to model complex properties such as covariance structure and skewness, but its parameter and entropy can still be estimated. We incorporate these features with an off-policy algorithm framework to solve problems with continuous action space and compare IDAC with state-of-the-art algorithms on representative OpenAI Gym environments. We observe that IDAC outperforms these baselines in most tasks. Python code is provided.

ICLR Conference 2020 Conference Paper

Meta-Learning without Memorization

• Mingzhang Yin
• George Tucker
• Mingyuan Zhou
• Sergey Levine
• Chelsea Finn

The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged as a promising technique for leveraging data from previous tasks to enable efficient learning of new tasks. However, most meta-learning algorithms implicitly require that the meta-training tasks be mutually-exclusive, such that no single model can solve all of the tasks at once. For example, when creating tasks for few-shot image classification, prior work uses a per-task random assignment of image classes to N-way classification labels. If this is not done, the meta-learner can ignore the task training data and learn a single model that performs all of the meta-training tasks zero-shot, but does not adapt effectively to new image classes. This requirement means that the user must take great care in designing the tasks, for example by shuffling labels or removing task identifying information from the inputs. In some domains, this makes meta-learning entirely inapplicable. In this paper, we address this challenge by designing a meta-regularization objective using information theory that places precedence on data-driven adaptation. This causes the meta-learner to decide what must be learned from the task training data and what should be inferred from the task testing input. By doing so, our algorithm can successfully use data from non-mutually-exclusive tasks to efficiently adapt to novel tasks. We demonstrate its applicability to both contextual and gradient-based meta-learning algorithms, and apply it in practical settings where applying standard meta-learning has been difficult. Our approach substantially outperforms standard meta-learning algorithms in these settings.

ICLR Conference 2020 Conference Paper

Mutual Information Gradient Estimation for Representation Learning

• Liangjian Wen
• Yiji Zhou
• Lirong He
• Mingyuan Zhou
• Zenglin Xu

Mutual Information (MI) plays an important role in representation learning. However, MI is unfortunately intractable in continuous and high-dimensional settings. Recent advances establish tractable and scalable MI estimators to discover useful representation. However, most of the existing methods are not capable of providing an accurate estimation of MI with low-variance when the MI is large. We argue that directly estimating the gradients of MI is more appealing for representation learning than estimating MI in itself. To this end, we propose the Mutual Information Gradient Estimator (MIGE) for representation learning based on the score estimation of implicit distributions. MIGE exhibits a tight and smooth gradient estimation of MI in the high-dimensional and large-MI settings. We expand the applications of MIGE in both unsupervised learning of deep representations based on InfoMax and the Information Bottleneck method. Experimental results have indicated significant performance improvement in learning useful representation.

UAI Conference 2020 Conference Paper

Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator

• Siamak Zamani Dadaneh
• Shahin Boluki
• Mingzhang Yin
• Mingyuan Zhou
• Xiaoning Qian

Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders (VAEs) with binary latent variables as hashing codes provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. Instead of solving the optimization for training relying on existing biased gradient estimators, an unbiased, low-variance gradient estimator, which evaluates the non-differentiable loss function over two correlated sets of binary hashing codes to control the gradient variance, is adopted to optimize the hashing function to achieve superior performance compared to the state-of-the-arts, as demonstrated by our comprehensive experiments.

ICML Conference 2020 Conference Paper

Recurrent Hierarchical Topic-Guided RNN for Language Generation

• Dandan Guo
• Bo Chen 0001
• Ruiying Lu
• Mingyuan Zhou

To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependencies. For inference, we develop a hybrid of stochastic-gradient Markov chain Monte Carlo and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.

IJCAI Conference 2020 Conference Paper

Switching Poisson Gamma Dynamical Systems

• Wenchao Chen
• Bo Chen
• Yicheng Liu
• Qianru Zhao
• Mingyuan Zhou

We propose Switching Poisson gamma dynamical systems (SPGDS) to model sequentially observed multivariate count data. Different from previous models, SPGDS assigns its latent variables into mixture of gamma distributed parameters to model complex sequences and describe the nonlinear dynamics, meanwhile, capture various temporal dependencies. For efficient inference, we develop a scalable hybrid stochastic gradient-MCMC and switching recurrent autoencoding variational inference, which is scalable to large scale sequences and fast in out-of-sample prediction. Experiments on both unsupervised and supervised tasks demonstrate that the proposed model not only has excellent fitting and prediction performance on complex dynamic sequences, but also separates different dynamical patterns within them.

ICML Conference 2020 Conference Paper

Thompson Sampling via Local Uncertainty

• Zhendong Wang 0005
• Mingyuan Zhou

Thompson sampling is an efficient algorithm for sequential decision making, which exploits the posterior uncertainty to address the exploration-exploitation dilemma. There has been significant recent interest in integrating Bayesian neural networks into Thompson sampling. Most of these methods rely on global variable uncertainty for exploration. In this paper, we propose a new probabilistic modeling framework for Thompson sampling, where local latent variable uncertainty is used to sample the mean reward. Variational inference is used to approximate the posterior of the local variable, and semi-implicit structure is further introduced to enhance its expressiveness. Our experimental results on eight contextual bandit benchmark datasets show that Thompson sampling guided by local uncertainty achieves state-of-the-art performance while having low computational complexity.

ICLR Conference 2020 Conference Paper

Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling

• Hao Zhang 0050
• Bo Chen 0001
• Long Tian
• Zhengjue Wang
• Mingyuan Zhou

For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework. VHE randomized GAN (VHE-GAN) encodes an image to decode its associated text, and feeds the variational posterior as the source of randomness into the GAN image generator. We plug three off-the-shelf modules, including a deep topic model, a ladder-structured image encoder, and StackGAN++, into VHE-GAN, which already achieves competitive performance. This further motivates the development of VHE-raster-scan-GAN that generates photo-realistic images in not only a multi-scale low-to-high-resolution manner, but also a hierarchical-semantic coarse-to-fine fashion. By capturing and relating hierarchical semantic and visual concepts with end-to-end training, VHE-raster-scan-GAN achieves state-of-the-art performance in a wide variety of image-text multi-modality learning and generation tasks.

ICML Conference 2019 Conference Paper

ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables

• Mingzhang Yin
• Yuguang Yue
• Mingyuan Zhou

To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation, REINFORCE, and Rao-Blackwellization to re-express the gradient as an expectation under the Dirichlet distribution, then uses variable swapping to construct differently expressed but equivalent expectations, and finally shares common random numbers between these expectations to achieve significant variance reduction. Experimental results show ARSM closely resembles the performance of the true gradient for optimization in univariate settings; outperforms existing estimators by a large margin when applied to categorical variational auto-encoders; and provides a "try-and-see self-critic" variance reduction method for discrete-action policy gradient, which removes the need of estimating baselines by generating a random number of pseudo actions and estimating their action-value functions.

ICML Conference 2019 Conference Paper

Convolutional Poisson Gamma Belief Network

• Chaojie Wang 0001
• Bo Chen 0001
• Sucheng Xiao
• Mingyuan Zhou

For text analysis, one often resorts to a lossy representation that either completely ignores word order or embeds each word as a low-dimensional dense feature vector. In this paper, we propose convolutional Poisson factor analysis (CPFA) that directly operates on a lossless representation that processes the words in each document as a sequence of high-dimensional one-hot vectors. To boost its performance, we further propose the convolutional Poisson gamma belief network (CPGBN) that couples CPFA with the gamma belief network via a novel probabilistic pooling layer. CPFA forms words into phrases and captures very specific phrase-level topics, and CPGBN further builds a hierarchy of increasingly more general phrase-level topics. For efficient inference, we develop both a Gibbs sampler and a Weibull distribution based convolutional variational auto-encoder. Experimental results demonstrate that CPGBN can extract high-quality text latent representations that capture the word order information, and hence can be leveraged as a building block to enrich a wide variety of existing latent variable models that ignore word order.

ICML Conference 2019 Conference Paper

Locally Private Bayesian Inference for Count Models

• Aaron Schein
• Zhiwei Steven Wu
• Alexandra Schofield
• Mingyuan Zhou
• Hanna M. Wallach

We present a general and modular method for privacy-preserving Bayesian inference for Poisson factorization, a broad class of models that includes some of the most widely used models in the social sciences. Our method satisfies limited-precision local privacy, a generalization of local differential privacy that we introduce to formulate appropriate privacy guarantees for sparse count data. We present an MCMC algorithm that approximates the posterior distribution over the latent variables conditioned on data that has been locally privatized by the geometric mechanism. Our method is based on two insights: 1) a novel reinterpretation of the geometric mechanism in terms of the Skellam distribution and 2) a general theorem that relates the Skellam and Bessel distributions. We demonstrate our method’s utility using two case studies that involve real-world email data. We show that our method consistently outperforms the commonly used naive approach, wherein inference proceeds as usual, treating the locally privatized data as if it were not privatized.

NeurIPS Conference 2019 Conference Paper

Poisson-Randomized Gamma Dynamical Systems

• Aaron Schein
• Scott Linderman
• Mingyuan Zhou
• David Blei
• Hanna Wallach

This paper presents the Poisson-randomized gamma dynamical system (PRGDS), a model for sequentially observed count tensors that encodes a strong inductive bias toward sparsity and burstiness. The PRGDS is based on a new motif in Bayesian latent variable modeling, an alternating chain of discrete Poisson and continuous gamma latent states that is analytically convenient and computationally tractable. This motif yields closed-form complete conditionals for all variables by way of the Bessel distribution and a novel discrete distribution that we call the shifted confluent hypergeometric distribution. We draw connections to closely related models and compare the PRGDS to these models in studies of real-world count data sets of text, international events, and neural spike trains. We find that a sparse variant of the PRGDS, which allows the continuous gamma latent states to take values of exactly zero, often obtains better predictive performance than other models and is uniquely capable of inferring latent structures that are highly localized in time.

NeurIPS Conference 2019 Conference Paper

Semi-Implicit Graph Variational Auto-Encoders

• Arman Hasanzadeh
• Ehsan Hajiramezanali
• Krishna Narayanan
• Nick Duffield
• Mingyuan Zhou
• Xiaoning Qian

Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable neighboring node sharing for better generative modeling of graph dependency structure, together with a Bernoulli-Poisson link decoder. Not only does this hierarchical construction provide a more flexible generative graph model to better capture real-world graph properties, but also does SIG-VAE naturally lead to semi-implicit hierarchical variational inference that allows faithful modeling of implicit posteriors of given graph data, which may exhibit heavy tails, multiple modes, skewness, and rich dependency structures. SIG-VAE integrates a carefully designed generative model, well suited to model real-world sparse graphs, and a sophisticated variational inference network, which propagates the graph structural information and distribution uncertainty to capture complex posteriors. SIG-VAE clearly outperforms a simple combination of VGAE with variational inference, including semi-implicit variational inference~(SIVI) or normalizing flow (NF), which does not propagate uncertainty in its inference network, and provides more interpretable latent representations than VGAE does. Extensive experiments with a variety of graph data show that SIG-VAE significantly outperforms state-of-the-art methods on several different graph analytic tasks.

NeurIPS Conference 2019 Conference Paper

Variational Graph Recurrent Neural Networks

• Ehsan Hajiramezanali
• Arman Hasanzadeh
• Krishna Narayanan
• Nick Duffield
• Mingyuan Zhou
• Xiaoning Qian

Representation learning over graph structured data has been mostly studied in static graph settings while efforts for modeling dynamic graphs are still scant. In this paper, we develop a novel hierarchical variational model that introduces additional latent random variables to jointly model the hidden states of a graph recurrent neural network (GRNN) to capture both topology and node attribute changes in dynamic graphs. We argue that the use of high-level latent random variables in this variational GRNN (VGRNN) can better capture potential variability observed in dynamic graphs as well as the uncertainty of node latent representation. With semi-implicit variational inference developed for this new VGRNN architecture (SI-VGRNN), we show that flexible non-Gaussian latent representations can further help dynamic graph analytic tasks. Our experiments with multiple real-world dynamic graph datasets demonstrate that SI-VGRNN and VGRNN consistently outperform the existing baseline and state-of-the-art methods by a significant margin in dynamic link prediction.

NeurIPS Conference 2018 Conference Paper

Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data

• Ehsan Hajiramezanali
• Siamak Zamani Dadaneh
• Alireza Karbalayghareh
• Mingyuan Zhou
• Xiaoning Qian

Precision medicine aims for personalized prognosis and therapeutics by utilizing recent genome-scale high-throughput profiling techniques, including next-generation sequencing (NGS). However, translating NGS data faces several challenges. First, NGS count data are often overdispersed, requiring appropriate modeling. Second, compared to the number of involved molecules and system complexity, the number of available samples for studying complex disease, such as cancer, is often limited, especially considering disease heterogeneity. The key question is whether we may integrate available data from all different sources or domains to achieve reproducible disease prognosis based on NGS count data. In this paper, we develop a Bayesian Multi-Domain Learning (BMDL) model that derives domain-dependent latent representations of overdispersed count data based on hierarchical negative binomial factorization for accurate cancer subtyping even if the number of samples for a specific cancer type is small. Experimental results from both our simulated and NGS datasets from The Cancer Genome Atlas (TCGA) demonstrate the promising potential of BMDL for effective multi-domain learning without ``negative transfer'' effects often seen in existing multi-task learning and transfer learning methods.

NeurIPS Conference 2018 Conference Paper

Deep Poisson gamma dynamical systems

• DanDan Guo
• Bo Chen
• Hao Zhang
• Mingyuan Zhou

We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies. Using sophisticated but simple-to-implement data augmentation techniques, we derived closed-form Gibbs sampling update equations by first backward and upward propagating auxiliary latent counts, and then forward and downward sampling latent variables. Moreover, we develop stochastic gradient MCMC inference that is scalable to very long multivariate count time series. Experiments on both synthetic and a variety of real-world data demonstrate that the proposed model not only has excellent predictive performance, but also provides highly interpretable multilayer latent structure to represent hierarchical and temporal information propagation.

NeurIPS Conference 2018 Conference Paper

Dirichlet belief networks for topic structure learning

• He Zhao
• Lan Du
• Wray Buntine
• Mingyuan Zhou

Recently, considerable research effort has been devoted to developing deep architectures for topic models to learn topic structures. Although several deep models have been proposed to learn better topic proportions of documents, how to leverage the benefits of deep structures for learning word distributions of topics has not yet been rigorously studied. Here we propose a new multi-layer generative process on word distributions of topics, where each layer consists of a set of topics and each topic is drawn from a mixture of the topics of the layer above. As the topics in all layers can be directly interpreted by words, the proposed model is able to discover interpretable topic hierarchies. As a self-contained module, our model can be flexibly adapted to different kinds of topic models to improve their modelling accuracy and interpretability. Extensive experiments on text corpora demonstrate the advantages of the proposed model.

ICML Conference 2018 Conference Paper

Inter and Intra Topic Structure Learning with Word Embeddings

• He Zhao 0001
• Lan Du 0002
• Wray L. Buntine
• Mingyuan Zhou

One important task of topic modeling for text analysis is interpretability. By discovering structured topics one is able to yield improved interpretability as well as modeling accuracy. In this paper, we propose a novel topic model with a deep structure that explores both inter-topic and intra-topic structures informed by word embeddings. Specifically, our model discovers inter topic structures in the form of topic hierarchies and discovers intra topic structures in the form of sub-topics, each of which is informed by word embeddings and captures a fine-grained thematic aspect of a normal topic. Extensive experiments demonstrate that our model achieves the state-of-the-art performance in terms of perplexity, document classification, and topic quality. Moreover, with topic hierarchies and sub-topics, the topics discovered in our model are more interpretable, providing an illuminating means to understand text data.

NeurIPS Conference 2018 Conference Paper

Masking: A New Perspective of Noisy Supervision

• Bo Han
• Jiangchao Yao
• Gang Niu
• Mingyuan Zhou
• Ivor Tsang
• Ya Zhang
• Masashi Sugiyama

It is important to learn various types of classifiers given training data with noisy labels. Noisy labels, in the most popular noise model hitherto, are corrupted from ground-truth labels by an unknown noise transition matrix. Thus, by estimating this matrix, classifiers can escape from overfitting those noisy labels. However, such estimation is practically difficult, due to either the indirect nature of two-step approaches, or not big enough data to afford end-to-end approaches. In this paper, we propose a human-assisted approach called ''Masking'' that conveys human cognition of invalid class transitions and naturally speculates the structure of the noise transition matrix. To this end, we derive a structure-aware probabilistic model incorporating a structure prior, and solve the challenges from structure extraction and structure alignment. Thanks to Masking, we only estimate unmasked noise transition probabilities and the burden of estimation is tremendously reduced. We conduct extensive experiments on CIFAR-10 and CIFAR-100 with three noise structures as well as the industrial-level Clothing1M with agnostic noise structure, and the results show that Masking can improve the robustness of classifiers significantly.

AAAI Conference 2018 Conference Paper

Multimodal Poisson Gamma Belief Network

• Chaojie Wang
• Bo Chen
• Mingyuan Zhou

To learn a deep generative model of multimodal data, we propose a multimodal Poisson gamma belief network (mPGBN) that tightly couple the data of different modalities at multiple hidden layers. The mPGBN unsupervisedly extracts a nonnegative latent representation using an upward-downward Gibbs sampler. It imposes sparse connections between different layers, making it simple to visualize the generative process and the relationships between the latent features of different modalities. Our experimental results on bi-modal data consisting of images and tags show that the mPGBN can easily impute a missing modality and hence is useful for both image annotation and retrieval. We further demonstrate that the mPGBN achieves state-of-the-art results on unsupervisedly extracting latent features from multimodal data.

NeurIPS Conference 2018 Conference Paper

Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risks

• Quan Zhang
• Mingyuan Zhou

We propose Lomax delegate racing (LDR) to explicitly model the mechanism of survival under competing risks and to interpret how the covariates accelerate or decelerate the time to event. LDR explains non-monotonic covariate effects by racing a potentially infinite number of sub-risks, and consequently relaxes the ubiquitous proportional-hazards assumption which may be too restrictive. Moreover, LDR is naturally able to model not only censoring, but also missing event times or event types. For inference, we develop a Gibbs sampler under data augmentation for moderately sized data, along with a stochastic gradient descent maximum a posteriori inference algorithm for big data applications. Illustrative experiments are provided on both synthetic and real datasets, and comparison with various benchmark algorithms for survival analysis with competing risks demonstrates distinguished performance of LDR.

NeurIPS Conference 2018 Conference Paper

Parsimonious Bayesian deep networks

• Mingyuan Zhou

Combining Bayesian nonparametrics and a forward model selection strategy, we construct parsimonious Bayesian deep networks (PBDNs) that infer capacity-regularized network architectures from the data and require neither cross-validation nor fine-tuning when training the model. One of the two essential components of a PBDN is the development of a special infinite-wide single-hidden-layer neural network, whose number of active hidden units can be inferred from the data. The other one is the construction of a greedy layer-wise learning algorithm that uses a forward model selection criterion to determine when to stop adding another hidden layer. We develop both Gibbs sampling and stochastic gradient descent based maximum a posteriori inference for PBDNs, providing state-of-the-art classification accuracy and interpretable data subtypes near the decision boundaries, while maintaining low computational complexity for out-of-sample prediction.

JMLR Journal 2018 Journal Article

Permuted and Augmented Stick-Breaking Bayesian Multinomial Regression

• Quan Zhang
• Mingyuan Zhou

To model categorical response variables given their covariates, we propose a permuted and augmented stick-breaking (paSB) construction that one-to-one maps the observed categories to randomly permuted latent sticks. This new construction transforms multinomial regression into regression analysis of stick-specific binary random variables that are mutually independent given their covariate-dependent stick success probabilities, which are parameterized by the regression coefficients of their corresponding categories. The paSB construction allows transforming an arbitrary cross-entropy-loss binary classifier into a Bayesian multinomial one. Specifically, we parameterize the negative logarithms of the stick failure probabilities with a family of covariate-dependent softplus functions to construct nonparametric Bayesian multinomial softplus regression, and transform Bayesian support vector machine (SVM) into Bayesian multinomial SVM. These Bayesian multinomial regression models are not only capable of providing probability estimates, quantifying uncertainty, increasing robustness, and producing nonlinear classification decision boundaries, but also amenable to posterior simulation. Example results demonstrate their attractive properties and performance. [abs] [ pdf ][ bib ] &copy JMLR 2018. ( edit, beta )

ICML Conference 2018 Conference Paper

Semi-Implicit Variational Inference

• Mingzhang Yin
• Mingyuan Zhou

Semi-implicit variational inference (SIVI) is introduced to expand the commonly used analytic variational distribution family, by mixing the variational parameter with a flexible distribution. This mixing distribution can assume any density function, explicit or not, as long as independent random samples can be generated via reparameterization. Not only does SIVI expand the variational family to incorporate highly flexible variational distributions, including implicit ones that have no analytic density functions, but also sandwiches the evidence lower bound (ELBO) between a lower bound and an upper bound, and further derives an asymptotically exact surrogate ELBO that is amenable to optimization via stochastic gradient ascent. With a substantially expanded variational family and a novel optimization algorithm, SIVI is shown to closely match the accuracy of MCMC in inferring the posterior in a variety of Bayesian inference tasks.

ICML Conference 2017 Conference Paper

Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC

• Yulai Cong
• Bo Chen 0001
• Hongwei Liu 0001
• Mingyuan Zhou

It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers. For the Poisson gamma belief network (PGBN), a recently proposed deep discrete LVM, we derive an alternative representation that is referred to as deep latent Dirichlet allocation (DLDA). Exploiting data augmentation and marginalization techniques, we derive a block-diagonal Fisher information matrix and its inverse for the simplex-constrained global model parameters of DLDA. Exploiting that Fisher information matrix with stochastic gradient MCMC, we present topic-layer-adaptive stochastic gradient Riemannian (TLASGR) MCMC that jointly learns simplex-constrained global parameters across all layers and topics, with topic and layer specific learning rates. State-of-the-art results are demonstrated on big data sets.

JMLR Journal 2016 Journal Article

Augmentable Gamma Belief Networks

• Mingyuan Zhou
• Yulai Cong
• Bo Chen

To infer multilayer deep representations of high-dimensional discrete and nonnegative real vectors, we propose an augmentable gamma belief network (GBN) that factorizes each of its hidden layers into the product of a sparse connection weight matrix and the nonnegative real hidden units of the next layer. The GBN's hidden layers are jointly trained with an upward-downward Gibbs sampler that solves each layer with the same subroutine. The gamma-negative binomial process combined with a layer-wise training strategy allows inferring the width of each layer given a fixed budget on the width of the first layer. Example results illustrate interesting relationships between the width of the first layer and the inferred network structure, and demonstrate that the GBN can add more layers to improve its performance in both unsupervisedly extracting features and predicting heldout data. For exploratory data analysis, we extract trees and subnetworks from the learned deep network to visualize how the very specific factors discovered at the first hidden layer and the increasingly more general factors discovered at deeper hidden layers are related to each other, and we generate synthetic data by propagating random variables through the deep network from the top hidden layer back to the bottom data layer. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )

ICML Conference 2016 Conference Paper

Bayesian Poisson Tucker Decomposition for Learning the Structure of International Relations

• Aaron Schein
• Mingyuan Zhou
• David M. Blei
• Hanna M. Wallach

We introduce Bayesian Poisson Tucker decomposition (BPTD) for modeling country–country interaction event data. These data consist of interaction events of the form “country i took action a toward country j at time t. ” BPTD discovers overlapping country–community memberships, including the number of latent communities. In addition, it discovers directed community–community interaction networks that are specific to “topics” of action types and temporal “regimes. ” We show that BPTD yields an efficient MCMC inference algorithm and achieves better predictive performance than related models. We also demonstrate that it discovers interpretable latent structure that agrees with our knowledge of international relations.

NeurIPS Conference 2016 Conference Paper

Poisson-Gamma dynamical systems

• Aaron Schein
• Hanna Wallach
• Mingyuan Zhou

This paper presents a dynamical system based on the Poisson-Gamma construction for sequentially observed multivariate count data. Inherent to the model is a novel Bayesian nonparametric prior that ties and shrinks parameters in a powerful way. We develop theory about the model's infinite limit and its steady-state. The model's inductive bias is demonstrated on a variety of real-world datasets where it is shown to learn interpretable structure and have superior predictive performance.

NeurIPS Conference 2015 Conference Paper

The Poisson Gamma Belief Network

• Mingyuan Zhou
• Yulai Cong
• Bo Chen

To infer a multilayer representation of high-dimensional count vectors, we propose the Poisson gamma belief network (PGBN) that factorizes each of its layers into the product of a connection weight matrix and the nonnegative real hidden units of the next layer. The PGBN's hidden layers are jointly trained with an upward-downward Gibbs sampler, each iteration of which upward samples Dirichlet distributed connection weight vectors starting from the first layer (bottom data layer), and then downward samples gamma distributed hidden units starting from the top hidden layer. The gamma-negative binomial process combined with a layer-wise training strategy allows the PGBN to infer the width of each layer given a fixed budget on the width of the first layer. The PGBN with a single hidden layer reduces to Poisson factor analysis. Example results on text analysis illustrate interesting relationships between the width of the first layer and the inferred network structure, and demonstrate that the PGBN, whose hidden units are imposed with correlated gamma priors, can add more layers to increase its performance gains over Poisson factor analysis, given the same limit on the width of the first layer.

NeurIPS Conference 2014 Conference Paper

Beta-Negative Binomial Process and Exchangeable Random Partitions for Mixed-Membership Modeling

• Mingyuan Zhou

The beta-negative binomial process (BNBP), an integer-valued stochastic process, is employed to partition a count vector into a latent random count matrix. As the marginal probability distribution of the BNBP that governs the exchangeable random partitions of grouped data has not yet been developed, current inference for the BNBP has to truncate the number of atoms of the beta process. This paper introduces an exchangeable partition probability function to explicitly describe how the BNBP clusters the data points of each group into a random number of exchangeable partitions, which are shared across all the groups. A fully collapsed Gibbs sampler is developed for the BNBP, leading to a novel nonparametric Bayesian topic model that is distinct from existing ones, with simple implementation, fast convergence, good mixing, and state-of-the-art predictive performance.

NeurIPS Conference 2012 Conference Paper

Augment-and-Conquer Negative Binomial Processes

• Mingyuan Zhou
• Lawrence Carin

By developing data augmentation methods unique to the negative binomial (NB) distribution, we unite seemingly disjoint count and mixture models under the NB process framework. We develop fundamental properties of the models and derive efficient Gibbs sampling inference. We show that the gamma-NB process can be reduced to the hierarchical Dirichlet process with normalization, highlighting its unique theoretical, structural and computational advantages. A variety of NB processes with distinct sharing mechanisms are constructed and applied to topic modeling, with connections to existing algorithms, showing the importance of inferring both the NB dispersion and probability parameters.

ICML Conference 2012 Conference Paper

Lognormal and Gamma Mixed Negative Binomial Regression

• Mingyuan Zhou
• Lingbo Li 0002
• David B. Dunson
• Lawrence Carin

UAI Conference 2012 Conference Paper

Nested Dictionary Learning for Hierarchical Organization of Imagery and Text

• Lingbo Li 0002
• XianXing Zhang
• Mingyuan Zhou
• Lawrence Carin

A tree-based dictionary learning model is developed for joint analysis of imagery and associated text. The dictionary learning may be applied directly to the imagery from patches, or to general feature vectors extracted from patches or superpixels (using any existing method for image feature extraction). Each image is associated with a path through the tree (from root to a leaf), and each of the multiple patches in a given image is associated with one node in that path. Nodes near the tree root are shared between multiple paths, representing image characteristics that are common among different types of images. Moving toward the leaves, nodes become specialized, representing details in image classes. If available, words (text) are also jointly modeled, with a path-dependent probability over words. The tree structure is inferred via a nested Dirichlet process, and a retrospective stick-breaking sampler is used to infer the tree depth and width.

ICML Conference 2011 Conference Paper

On the Integration of Topic Modeling and Dictionary Learning

• Lingbo Li 0002
• Mingyuan Zhou
• Guillermo Sapiro
• Lawrence Carin

NeurIPS Conference 2009 Conference Paper

Non-Parametric Bayesian Dictionary Learning for Sparse Image Representations

• Mingyuan Zhou
• Haojun Chen
• Lu Ren
• Guillermo Sapiro
• Lawrence Carin
• John Paisley

Non-parametric Bayesian techniques are considered for learning dictionaries for sparse image representations, with applications in denoising, inpainting and compressive sensing (CS). The beta process is employed as a prior for learning the dictionary, and this non-parametric method naturally infers an appropriate dictionary size. The Dirichlet process and a probit stick-breaking process are also considered to exploit structure within an image. The proposed method can learn a sparse dictionary in situ; training images may be exploited if available, but they are not required. Further, the noise variance need not be known, and can be non-stationary. Another virtue of the proposed method is that sequential inference can be readily employed, thereby allowing scaling to large images. Several example results are presented, using both Gibbs and variational Bayesian inference, with comparisons to other state-of-the-art approaches.