Author name cluster

Jie Ren

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

23 papers

2 author rows

AAAI Conference 2025 Conference Paper

HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection

Zican Shi
Jing Hu
Jie Ren
Hengkang Ye
Xuyang Yuan
Yan Ouyang
Jia He
Bo Ji

The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it does not directly enhance or enrich the features of tiny objects. Furthermore, FPN lacks spatial perception ability. To address these issues, we propose a novel High Frequency and Spatial Perception Feature Pyramid Network (HS-FPN) with two innovative modules. First, we designed a high frequency perception module (HFP) that generates high frequency responses through high pass filters. These high frequency responses are used as mask weights from both spatial and channel perspectives to enrich and highlight the features of tiny objects in the original feature maps. Second, we developed a spatial dependency perception module (SDP) to capture the spatial dependencies that FPN lacks. Our experiments demonstrate that detectors based on HS-FPN exhibit competitive advantages over state-of-the-art models on the AI-TOD dataset for tiny object detection.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

Jie Ren
Zhenwei Dai
Xianfeng Tang
Yue Xing
Shenglai Zeng
Jingying Zeng
Qiankun Peng
Samarth Varshney

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these concerns, unlearning techniques have been developed to remove the influence of specific data without retraining from scratch. However, this paper reveals a critical vulnerability in fine-tuning-based unlearning: a malicious user can craft a manipulated forgetting request that stealthily degrades the model’s utility for benign users. We demonstrate this risk through a red-teaming Stealthy Attack (SA), which is inspired by two key limitations of existing unlearning—the inability to constrain the scope of unlearning effect and the failure to distinguish benign tokens from unlearning signals. Prior work has shown that unlearned models tend to memorize forgetting data as unlearning signals, and respond with hallucinations or feigned ignorance when unlearning signals appear in the input. By subtly increasing the presence of common benign tokens in the forgetting data, SA enhances the connection between benign tokens and unlearning signals. As a result, when normal users include such tokens in their prompts, the model exhibits unlearning behaviors, leading to unintended utility degradation. To address this vulnerability, we propose Scope-aware Unlearning (SU), a lightweight enhancement that introduces a scope term into the unlearning objective, encouraging the model to localize the forgetting effect. Our method requires no additional data processing, integrates seamlessly with existing fine-tuning frameworks, and significantly improves robustness against SA. Extensive experiments validate the effectiveness of both SA and SU.

PDF Details

IROS Conference 2025 Conference Paper

L2Calib: SE (3)-Manifold Reinforcement Learning for Robust Extrinsic Calibration with Degenerate Motion Resilience

Baorun Li
Chengrui Zhu
Siyi Du
Bingran Chen
Jie Ren
Wenfei Wang
Yong Liu 0007
Jiajun Lv

Extrinsic calibration is essential for multi-sensor fusion, existing methods rely on structured targets or fully-excited data, limiting real-world applicability. Online calibration further suffers from weak excitation, leading to unreliable estimates. To address these limitations, we propose a reinforcement learning (RL)-based extrinsic calibration framework that formulates extrinsic calibration as a decisionmaking problem, directly optimizes SE(3) extrinsics to enhance odometry accuracy. Our approach leverages a probabilistic Bingham distribution to model 3D rotations, ensuring stable optimization while inherently retaining quaternion symmetry. A trajectory alignment reward mechanism enables robust calibration without structured targets by quantitatively evaluating estimated tightly-coupled trajectory against a reference trajectory. Additionally, an automated data selection module filters uninformative samples, significantly improving efficiency and scalability for large-scale datasets. Extensive experiments on UAVs, UGVs, and handheld platforms demonstrate that our method outperforms traditional optimization-based approaches, achieving high-precision calibration even under weak excitation conditions. Our framework simplifies deployment on diverse robotic platforms by eliminating the need for high-quality initial extrinsics and enabling calibration from routine operating data. The code is available at https://github.com/APRIL-ZJU/learn-to-calibrate.

Details

AAAI Conference 2025 Conference Paper

Monitoring Primitive Interactions During the Training of DNNs

Jie Ren
Xinhao Zheng
Jiyu Liu
Andrew Lizarraga
Ying Nian Wu
Liang Lin
Quanshi Zhang

This paper focuses on the newly emerged research topic, i.e., whether the complex decision-making logic of a DNN can be mathematically summarized into a few simple logics. Beyond the explanation of a static DNN, in this paper, we hope to show that the seemingly complex learning dynamics of a DNN can be faithfully represented as the change of a few primitive interaction patterns encoded by the DNN. Therefore, we redefine the interaction of principal feature components in intermediate-layer features, which enables us to concisely summarize the highly complex dynamics of interactions throughout the learning of the DNN. The mathematical faithfulness of the new interaction is experimentally verified. From the perspective of learning efficiency, we find that the interactions naturally belong to five groups (reliable, withdrawn, forgotten, betraying, and fluctuating interactions), each representing a distinct type of dynamics of an interaction being learned and/or being forgotten. This provides deep insights into the learning process of a DNN.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Optimizing Personalized Federated Learning Through Adaptive Layer-Wise Learning

Weihang Chen
Cheng Yang
Jie Ren
Zhiqiang Li
Zheng Wang

Real-life deployment of federated Learning (FL) often faces non-IID data, which leads to poor accuracy and slow convergence. Personalized FL (pFL) tackles these issues by tailoring local models to individual data sources and using weighted aggregation methods for client-specific learning. However, existing pFL methods often fail to provide each local model with global knowledge on demand while maintaining low computational overhead. Additionally, local models tend to over-personalize their data during the training process, potentially dropping previously acquired global information. We propose FLAYER, a novel layer-wise learning method for pFL that optimizes local model personalization performance. FLAYER considers the different roles and learning abilities of neural network layers of individual local models. It incorporates global information for each local model as needed to initialize the local model cost-effectively. It then dynamically adjusts learning rates for each layer during local training, optimizing the personalized learning process for each local model while preserving global knowledge. Additionally, to enhance global representation in pFL, FLAYER selectively uploads parameters for global aggregation in a layer-wise manner. We evaluate FLAYER on four representative datasets in computer vision and natural language processing domains. Compared to eight state-of-the-art pFL methods, FLAYER improves the inference accuracy, on average, by 5. 20% (up to 14. 29%). Code is available at https: //github. com/lancasterJie/FLAYER/.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Private Training Large-scale Models with Efficient DP-SGD

Liangyu Wang
Junxiao Wang
Jie Ren
Zihang Xiang
David Keyes
Di Wang

As large language models (LLMs) increasingly underpin technological advancements, the privacy of their training data emerges as a critical concern. Differential Privacy (DP) serves as a rigorous mechanism to protect this data, yet its integration via Differentially Private Stochastic Gradient Descent (DP-SGD) introduces substantial challenges, primarily due to the complexities of per-sample gradient clipping. Current explicit methods, such as Opacus, necessitate extensive storage for per-sample gradients, significantly inflating memory requirements. Conversely, implicit methods like GhostClip reduce storage needs by recalculating gradients multiple times, which leads to inefficiencies due to redundant computations. This paper introduces FlashDP, an innovative cache-friendly per-layer DP-SGD that consolidates necessary operations into a single task, calculating gradients only once in a fused manner. This approach not only diminishes memory movement by up to 50\% but also cuts down redundant computations by 20\%, compared to previous methods. Consequently, FlashDP does not increase memory demands and achieves a 90\% throughput compared to the Non-DP method on a four-A100 system during the pre-training of the Llama-13B model, while maintaining parity with standard per-layer clipped DP-SGD in terms of accuracy. These advancements establish FlashDP as a pivotal development for efficient and privacy-preserving training of LLMs. FlashDP's code has been open-sourced in https: //github. com/kaustpradalab/flashdp.

PDF Details

ICLR Conference 2025 Conference Paper

Revisiting Mode Connectivity in Neural Networks with Bezier Surface

Jie Ren
Pin-Yu Chen
Ren Wang 0008

Understanding the loss landscapes of neural networks (NNs) is critical for optimizing model performance. Previous research has identified the phenomenon of mode connectivity on curves, where two well-trained NNs can be connected by a continuous path in parameter space where the path maintains nearly constant loss. In this work, we extend the concept of mode connectivity to explore connectivity on surfaces, significantly broadening its applicability and unlocking new opportunities. While initial attempts to connect models via linear surfaces in parameter space were unsuccessful, we propose a novel optimization technique that consistently discovers Bézier surfaces with low-loss and high-accuracy connecting multiple NNs in a nonlinear manner. We further demonstrate that even without optimization, mode connectivity exists in certain cases of Bézier surfaces, where the models are carefully selected and combined linearly. This approach provides a deeper and more comprehensive understanding of the loss landscape and offers a novel way to identify models with enhanced performance for model averaging and output ensembling. We demonstrate the effectiveness of our method on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets using VGG16, ResNet18, and ViT architectures.

Details

TMLR Journal 2025 Journal Article

SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling

Jiefeng Chen
Jie Ren
Xinyun Chen
Chengrun Yang
Ruoxi Sun
Jinsung Yoon
Sercan O Arik

Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel methods like repeated sampling are often inefficient and quickly saturate, while sequential methods like SELF-REFINE struggle to improve after a few rounds. Although combining these approaches shows promise, current methods require fine-tuned reward and revision models. This paper proposes Self-Enhanced Test-Time Scaling (SETS), a simple yet effective approach that overcomes these limitations by strategically combining parallel and sequential techniques and fully leveraging LLMs' self-improvement abilities. SETS exploits the inherent self-verification and self-correction capabilities of LLMs, unifying sampling, verification, and correction within a single framework. This facilitates efficient and scalable test-time computation for enhanced performance on complex tasks without any model training. Our comprehensive experimental results on challenging benchmarks spanning planning, reasoning, math, and coding demonstrate that SETS achieves significant performance improvements and more advantageous test-time scaling behavior than the alternatives.

PDF Details

YNIMG Journal 2025 Journal Article

The neural representation of body orientation and emotion from biological motion

Shuaicheng Liu
Lu Yu
Jie Ren
Mingming Zhang
Wenbo Luo

The perception of human body orientation and emotion in others provides crucial insights into their intentions. While significant research has explored the brain's representation of body orientation and emotion processing, their possible combined representation remains less well understood. In this study, functional magnetic resonance imaging was employed to investigate this issue. Participants were shown point-light displays and tasked with recognizing both body emotion and orientation. The analysis of functional activation revealed that the extrastriate body area encodesd emotion, while the precentral gyrus and postcentral gyrus encoded body orientation. Additionally, results from multivariate pattern analysis and representational similarity analysis demonstrated that the lingual gyrus, precentral gyrus, and postcentral gyrus played a critical role in processing body orientation, whereas the lingual gyrus and extrastriate body area were crucial for processing emotion. Furthermore, the commonality analysis found that the neural representations of emotion and body orientation in the lingual and precentral gyrus were not interacting, but rather competing. Lastly, a remarkable interaction between hemisphere and body orientation revealed in the connection analysis showed that the coupling between the inferior parietal lobule and the left precentral gyrus was more sensitive to a 90° body orientation, while the coupling between the inferior parietal lobule and the right precentral gyrus was sensitive to 0° and 45° body orientation. Overall, these findings suggest that the conflicted relationship between the neural representation of body orientation and emotion in LING and PreCG when point-light displays were shown, and the different hemispheres play different role in encoding different body orientations.

Details DOI

NeurIPS Conference 2024 Conference Paper

Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model

Yanpeng Ye
Jie Ren
Shaozhou Wang
Yuwei Wan
Imran Razzak
Bram Hoex
Haofeng Wang
Tong Xie

Knowledge in materials science is widely dispersed across extensive scientific literature, posing significant challenges for efficient discovery and integration of new materials. Traditional methods, often reliant on costly and time-consuming experimental approaches, further complicate rapid innovation. Addressing these challenges, the integration of artificial intelligence with materials science has opened avenues for accelerating the discovery process, though it also demands precise annotation, data extraction, and traceability of information. To tackle these issues, this article introduces the Materials Knowledge Graph (MKG), which utilizes advanced natural language processing techniques, integrated with large language models to extract and systematically organize a decade's worth of high-quality research into structured triples, contains 162, 605 nodes and 731, 772 edges. MKG categorizes information into comprehensive labels such as Name, Formula, and Application, structured around a meticulously designed ontology, thus enhancing data usability and integration. By implementing network-based algorithms, MKG not only facilitates efficient link prediction but also significantly reduces reliance on traditional experimental methods. This structured approach not only streamlines materials research but also lays the groundwork for more sophisticated materials knowledge graphs.

PDF Details DOI

EAAI Journal 2024 Journal Article

Multi-mode filter target tracking method for mobile robot using multi-agent reinforcement learning

Xiaofeng Li
Jie Ren
Yunbo Li

Multi-mode filtering target tracking for mobile robot has important research significance for robot path planning, motion control and tracking robot targets. To address the problem that it is difficult for mobile robot to track targets in unknown environments, a multi-mode filtering target tracking method for mobile robot using multi-agent reinforcement learning is proposed. First, based on the extended kalman filter and combined with probability data association, the observation values in different motion modes are calculated and the system state is updated in real time, to achieve concurrent mapping, location and state estimation for each robot. Second, state communication among multi-mobile robot are established, and the multi-agent reinforcement learning model is built. Finally, based on the agent reinforcement learning model, based on the communication and communication among multi-tracking agents and the location of the target agent, the target tracking task is allocated to shorten the total path of the tracking agent, and the multi-target tracking of multi-mobile robot is completed by constantly learning and updating the strategy. The results show that the maximum tracking error of the target is 7 mm, and the calculation time of each step is only 51. 1ms. The tracking success rate, observation rate and coverage rate are all high. It has important research value in robot location and navigation, service robot and other fields.

Details DOI

TMLR Journal 2024 Journal Article

Stealthy Backdoor Attack via Confidence-driven Sampling

Pengfei He
Yue Xing
Han Xu
Jie Ren
Yingqian Cui
Shenglai Zeng
Jiliang Tang
Makoto Yamada

Backdoor attacks facilitate unauthorized control in the testing stage by carefully injecting harmful triggers during the training phase of deep neural networks. Previous works have focused on improving the stealthiness of the trigger while randomly selecting samples to attack. However, we find that random selection harms the stealthiness of the model. In this paper, we identify significant pitfalls of random sampling, which make the attacks more detectable and easier to defend against. To improve the stealthiness of existing attacks, we introduce a method of strategically poisoning samples near the model's decision boundary, aiming to minimally alter the model's behavior (decision boundary) before and after backdooring. Our main insight for detecting boundary samples is exploiting the confidence scores as a metric for being near the decision boundary and selecting those to poison (inject) the attack. The proposed approach makes it significantly harder for defenders to identify the attacks. Our method is versatile and independent of any specific trigger design. We provide theoretical insights and conduct extensive experiments to demonstrate the effectiveness of the proposed method.

PDF Details

JMLR Journal 2023 Journal Article

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

Jeremiah Zhe Liu
Shreyas Padhy
Jie Ren
Zi Lin
Yeming Wen
Ghassen Jerfel
Zachary Nado
Jasper Snoek

Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles. However their practicality in real-time, industrial-scale applications are limited due to the high memory and computational cost. Furthermore, ensembles and BNNs do not necessarily fix all the issues with the underlying member networks. In this work, we study principled approaches to improve the uncertainty property of a single network, based on a single, deterministic representation. By formalizing the uncertainty quantification as a minimax learning problem, we first identify distance awareness, i.e., the model's ability to quantify the distance of a testing example from the training data, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs with two simple changes: (1) applying spectral normalization to hidden weights to enforce bi-Lipschitz smoothness in representations and (2) replacing the last output layer with a Gaussian process layer. On a suite of vision and language understanding benchmarks and on modern architectures (Wide-ResNet and BERT), SNGP consistently outperforms other single-model approaches in prediction, calibration and out-of-domain detection. Furthermore, SNGP provides complementary benefits to popular techniques such as deep ensembles and data augmentation, making it a simple and scalable building block for probabilistic deep learning. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

PDF Details

AAAI Conference 2023 Conference Paper

DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-Aided Drug Discovery – a Focus on Affinity Prediction Problems with Noise Annotations

Yuanfeng Ji
Lu Zhang
Jiaxiang Wu
Bingzhe Wu
Lanqing Li
Long-Kai Huang
Tingyang Xu
Yu Rong

AI-aided drug discovery (AIDD) is gaining popularity due to its potential to make the search for new pharmaceuticals faster, less expensive, and more effective. Despite its extensive use in numerous fields (e.g., ADMET prediction, virtual screening), little research has been conducted on the out-of-distribution (OOD) learning problem with noise. We present DrugOOD, a systematic OOD dataset curator and benchmark for AIDD. Particularly, we focus on the drug-target binding affinity prediction problem, which involves both macromolecule (protein target) and small-molecule (drug compound). DrugOOD offers an automated dataset curator with user-friendly customization scripts, rich domain annotations aligned with biochemistry knowledge, realistic noise level annotations, and rigorous benchmarking of SOTA OOD algorithms, as opposed to only providing fixed datasets. Since the molecular data is often modeled as irregular graphs using graph neural network (GNN) backbones, DrugOOD also serves as a valuable testbed for graph OOD learning problems. Extensive empirical studies have revealed a significant performance gap between in-distribution and out-of-distribution experiments, emphasizing the need for the development of more effective schemes that permit OOD generalization under noise for AIDD.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning

Bo Liu
Xidong Feng
Jie Ren
Luo Mai
Rui Zhu
Haifeng Zhang
Jun Wang
Yaodong Yang

Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations. In this paper, we develop a unified framework that describes variations of GMRL algorithms and points out that existing stochastic meta-gradient estimators adopted by GMRL are actually \textbf{biased}. Such meta-gradient bias comes from two sources: 1) the compositional bias incurred by the two-level problem structure, which has an upper bound of $\mathcal{O}\big(K\alpha^{K}\hat{\sigma}_{\text{In}}|\tau|^{-0. 5}\big)$ \emph{w. r. t. } inner-loop update step $K$, learning rate $\alpha$, estimate variance $\hat{\sigma}^{2}_{\text{In}}$ and sample size $|\tau|$, and 2) the multi-step Hessian estimation bias $\hat{\Delta}_{H}$ due to the use of autodiff, which has a polynomial impact $\mathcal{O}\big((K-1)(\hat{\Delta}_{H})^{K-1}\big)$ on the meta-gradient bias. We study tabular MDPs empirically and offer quantitative evidence that testifies our theoretical findings on existing stochastic meta-gradient estimators. Furthermore, we conduct experiments on Iterated Prisoner's Dilemma and Atari games to show how other methods such as off-policy learning and low-bias estimator can help fix the gradient bias for GMRL algorithms in general.

PDF Details

EAAI Journal 2022 Journal Article

Depth-aware gaze-following via auxiliary networks for robotics

Tianlei Jin
Qizhi Yu
Shiqiang Zhu
Zheyuan Lin
Jie Ren
Yuanhai Zhou
Wei Song

Gaze-Following aims to predict the gaze target of a subject within an image, and information on orientation and depth greatly improves this task. However, previous methods require additional datasets to obtain depth or orientation information, leading to cumbersome training or inference processes. To this end, we propose an end-to-end depth-aware gaze-following approach that incorporates depth and orientation information without additional datasets. Our approach identifies a primary task, gaze-following, supervised by true labels from the gaze-following dataset and two auxiliary tasks, scene depth estimation and 3D orientation estimation, supervised by generated pseudo labels. Intermediate auxiliary features are integrated into the primary task network as implicit information. We propose a residual filter module for screening useful information that can enhance gaze-following prediction performance. Extensive experiments on GazeFollow and VideoAttentionTarget show that our approach achieves state-of-the-art results (0. 120 Ave. Dist. achieved on GazeFollow and 0. 104 L2 Dist. achieved on VideoAttentionTarget). Finally, we apply our approach to a real robot for understanding human attention and intention. Compared to the previous depth considered gaze-following method, our method saves half of the computation time.

Details DOI

NeurIPS Conference 2022 Conference Paper

Pluralistic Image Completion with Gaussian Mixture Models

Xiaobo Xia
Wenhao Yang
Jie Ren
Yewen Li
Yibing Zhan
Bo Han
Tongliang Liu

Pluralistic image completion focuses on generating both visually realistic and diverse results for image completion. Prior methods enjoy the empirical successes of this task. However, their used constraints for pluralistic image completion are argued to be not well interpretable and unsatisfactory from two aspects. First, the constraints for visual reality can be weakly correlated to the objective of image completion or even redundant. Second, the constraints for diversity are designed to be task-agnostic, which causes the constraints to not work well. In this paper, to address the issues, we propose an end-to-end probabilistic method. Specifically, we introduce a unified probabilistic graph model that represents the complex interactions in image completion. The entire procedure of image completion is then mathematically divided into several sub-procedures, which helps efficient enforcement of constraints. The sub-procedure directly related to pluralistic results is identified, where the interaction is established by a Gaussian mixture model (GMM). The inherent parameters of GMM are task-related, which are optimized adaptively during training, while the number of its primitives can control the diversity of results conveniently. We formally establish the effectiveness of our method and demonstrate it with comprehensive experiments. The implementationis available at https: //github. com/tmllab/PICMM.

PDF Details

NeurIPS Conference 2021 Conference Paper

Exploring the Limits of Out-of-Distribution Detection

Stanislav Fort
Jie Ren
Balaji Lakshminarayanan

Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities. For instance, on CIFAR-100 vs CIFAR-10 OOD detection, we improve the AUROC from 85% (current SOTA) to more than 96% using Vision Transformers pre-trained on ImageNet21k. On a challenging genomics OOD detection benchmark, we improve the AUROC from 66% to 77% using transformer and unsupervised pre-training. To further improve performance, we explore the few-shot outlier exposure setting where a few examples from outlier classes may be available; we show that pre-trained transformers are particularly well-suited for outlier exposure, and that the AUROC of OOD detection on CIFAR-100 vs CIFAR-10 can be improved to 98. 7% with just 1 image per OOD class, and 99. 46% with 10 images per OOD class. For multi-modal image-text pre-trained transformers such as CLIP, we explore a new way of using just the names of outlier classes as a sole source of information without any accompanying images, and show that this outperforms previous SOTA on standard OOD benchmark tasks.

PDF Details

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.

Details

NeurIPS Conference 2021 Conference Paper

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Jie Ren
Die Zhang
Yisen Wang
Lu Chen
Zhanpeng Zhou
Yiting Chen
Xu Cheng
Xin Wang

This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that adversarial attacks mainly affect high-order interactions to fool the DNN. Furthermore, we find that the robustness of adversarially trained DNNs comes from category-specific low-order interactions. Our findings provide a potential method to unify adversarial perturbations and robustness, which can explain the existing robustness-boosting methods in a principle way. Besides, our findings also make a revision of previous inaccurate understanding of the shape bias of adversarially learned features. Our code is available online at https: //github. com/Jie-Ren/A-Unified-Game-Theoretic-Interpretation-of-Adversarial-Robustness.

PDF Details

NeurIPS Conference 2020 Conference Paper

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

Jie Ren
Minjia Zhang
Dong Li

The state-of-the-art approximate nearest neighbor search (ANNS) algorithms face a fundamental tradeoff between query latency and accuracy, because of small main memory capacity: To store indices in main memory for short query latency, the ANNS algorithms have to limit dataset size or use a quantization scheme which hurts search accuracy. The emergence of heterogeneous memory (HM) brings a solution to significantly increase memory capacity and break the above tradeoff: Using HM, billions of data points can be placed in the main memory on a single machine without using any data compression. However, HM consists of both fast (but small) memory and slow (but large) memory, and using HM inappropriately slows down query significantly. In this work, we present a novel graph-based similarity search algorithm called HM-ANN, which takes both memory and data heterogeneity into consideration and enables billion-scale similarity search on a single node without using compression. On two billion-sized datasets BIGANN and DEEP1B, HM-ANN outperforms state-of-the-art compression-based solutions such as L&C and IMI+OPQ in recall-vs-latency by a large margin, obtaining 46% higher recall under the same search latency. We also extend existing graph-based methods such as HNSW and NSG with two strong baseline implementations on HM. At billion-point scale, HM-ANN is 2X and 5. 8X faster than our HNSWand NSG baselines respectively to reach the same accuracy.

PDF Details

NeurIPS Conference 2019 Conference Paper

Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift

Yaniv Ovadia
Emily Fertig
Jie Ren
Zachary Nado
D. Sculley
Sebastian Nowozin
Joshua Dillon
Balaji Lakshminarayanan

Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive uncertainty. Quantifying uncertainty is especially critical in real-world settings, which often involve input distributions that are shifted from the training distribution due to a variety of factors including sample bias and non-stationarity. In such settings, well calibrated uncertainty estimates convey information about when a model's output should (or should not) be trusted. Many probabilistic deep learning methods, including Bayesian-and non-Bayesian methods, have been proposed in the literature for quantifying predictive uncertainty, but to our knowledge there has not previously been a rigorous large-scale empirical comparison of these methods under dataset shift. We present a large-scale benchmark of existing state-of-the-art methods on classification problems and investigate the effect of dataset shift on accuracy and calibration. We find that traditional post-hoc calibration does indeed fall short, as do several other previous methods. However, some methods that marginalize over models give surprisingly strong results across a broad spectrum of tasks.

PDF Details

NeurIPS Conference 2019 Conference Paper

Likelihood Ratios for Out-of-Distribution Detection

Jie Ren
Peter Liu
Emily Fertig
Jasper Snoek
Ryan Poplin
Mark Depristo
Joshua Dillon
Balaji Lakshminarayanan

Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distribution (OOD) inputs, the prediction may not only be erroneous, but confidently so, limiting the safe deployment of classifiers in real-world applications. One such challenging application is bacteria identification based on genomic sequences, which holds the promise of early detection of diseases, but requires a model that can output low confidence predictions on OOD genomic sequences from new bacteria that were not present in the training data. We introduce a genomics dataset for OOD detection that allows other researchers to benchmark progress on this important problem. We investigate deep generative model based approaches for OOD detection and observe that the likelihood score is heavily affected by population level background statistics. We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics. We benchmark the OOD detection performance of the proposed method against existing approaches on the genomics dataset and show that our method achieves state-of-the-art performance. Finally, we demonstrate the generality of the proposed method by showing that it significantly improves OOD detection when applied to deep generative models of images.

PDF Details