Author name cluster

Yang Feng

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.

30 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

A Latent Multilayer Graphical Model For Complex, Interdependent Systems

Martin Ondrus
Ivor Cribben
Yang Feng

Networks have been extensively used and have provided novel insights across a wide variety of research areas. However, many real-world systems are, in fact, a ``network of networks'', or a multilayer network, which interact as components of a larger multimodal system. A major difficulty in this multilayer framework is the estimation of interlayer edges or connections. In this work, we propose a new estimation method, called multilayer sparse + low-rank inverse covariance estimation (multiSLICE), which estimates the interlayer edges. multiSLICE bridges latent variable Gaussian graphical methods with multilayer networks, offering a flexible framework for modeling processes with irregular sampling and heterogeneous graph structures. We develop an effective algorithm to compute the estimator. We also establish theoretical conditions for the recoverability of the joint space, analyze how inter-layer interactions influence joint parameter estimation, and provide theoretical bounds on their relationships. Finally, we rigorously evaluate our method on both simulated and multimodal neuroimaging data, demonstrating improvements over state-of-the-art approaches. Finally, all the relevant R code implementing the method in the article is available on GitHub.

ICLR Conference 2025 Conference Paper

Differentiable Rule Induction from Raw Sequence Inputs

Kun Gao 0003
Katsumi Inoue
Yongzhi Cao
Hanpin Wang
Yang Feng

Rule learning-based models are widely used in highly interpretable scenarios due to their transparent structures. Inductive logic programming (ILP), a form of machine learning, induces rules from facts while maintaining interpretability. Differentiable ILP models enhance this process by leveraging neural networks to improve robustness and scalability. However, most differentiable ILP methods rely on symbolic datasets, facing challenges when learning directly from raw data. Specifically, they struggle with explicit label leakage: The inability to map continuous inputs to symbolic variables without explicit supervision of input feature labels. In this work, we address this issue by integrating a self-supervised differentiable clustering model with a novel differentiable ILP model, enabling rule learning from raw data without explicit label leakage. The learned rules effectively describe raw data through its features. We demonstrate that our method intuitively and precisely learns generalized rules from time series and image data.

NeurIPS Conference 2025 Conference Paper

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

Zhengrui Ma
Yang Feng
Chenze Shao
Fandong Meng
Jie Zhou
Min Zhang

We introduce \emph{SLED}, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy distance offers an analytical measure of the distributional gap by contrasting simulated and target samples, enabling efficient training to capture the underlying continuous autoregressive distribution. By bypassing reliance on residual vector quantization, SLED avoids discretization errors and eliminates the need for the complicated hierarchical architectures common in existing speech language models. It simplifies the overall modeling pipeline while preserving the richness of speech information and maintaining inference efficiency. Empirical results demonstrate that SLED achieves strong performance in both zero-shot and streaming speech synthesis, showing its potential for broader applications in general-purpose speech language models. Demos and code are available at \url{https: //github. com/ictnlp/SLED-TTS}.

NeurIPS Conference 2025 Conference Paper

FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing

Shoutao Guo
Shaolei Zhang
Qingkai Fang
Zhengrui Ma
Min Zhang
Yang Feng

The rapid advancement of Large Language Models (LLMs) has spurred significant progress in Large Speech-Language Models (LSLMs), enhancing their capabilities in both speech understanding and generation. While existing LSLMs often concentrate on augmenting speech generation or tackling a diverse array of short-speech tasks, the efficient processing of long-form speech remains a critical yet underexplored challenge. This gap is primarily attributed to the scarcity of long-speech training datasets and the high computational costs associated with long sequences. To address these limitations, we introduce FastLongSpeech, a novel framework designed to extend LSLM capabilities for efficient long-speech processing without necessitating dedicated long-speech training data. FastLongSpeech incorporates an iterative fusion strategy that can compress excessively long-speech sequences into manageable lengths. To adapt LSLMs for long-speech inputs, it introduces a dynamic compression training approach, which exposes the model to short-speech sequences at varying compression ratios, thereby transferring the capabilities of LSLMs to long-speech tasks. To assess the long-speech capabilities of LSLMs, we develop a long-speech understanding benchmark called LongSpeech-Eval. Experiments show that our method exhibits strong performance in both long-speech and short-speech tasks, while greatly improving inference efficiency.

IROS Conference 2025 Conference Paper

GeoSafe: A Unified Unconstrained Multi-DOF Optimization Framework for Multi-UAV Cooperative Hoisting and Obstacle Avoidance

Xingyu Li
Hongyu Nie
Haoxuan Xu
Xingrui Liu
Zhaotong Tan
Chunyu Jiang
Yang Feng
Sen Mei

In warehouse logistics and post-disaster rescue, multi-UAV payload transport must navigate tight spaces, such as 1. 2m × 0. 8m aisles and collapsed pipelines as narrow as 0. 6m. Traditional four-DOF (translation and scaling) trajectory planning struggles under such constraints. To overcome this, we propose an optimization-based framework that introduces rotational degrees of freedom, expanding the solution space to five dimensions. Using the MINCO transformation, we reformulate constrained formation adjustment into an unconstrained optimization problem via smooth mappings and penalty functions, enabling simultaneous obstacle avoidance and formation control. The GeoSafe algorithm further enhances safe passage by integrating iterative region expansion and semi-definite programming to maximize obstacle-free space. Extensive simulations and real-world experiments show our method’s superiority over sampling-based and IF-based approaches in narrow passage traversal, computational efficiency, and formation scalability.

AAAI Conference 2025 Conference Paper

Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation

Shoutao Guo
Shaolei Zhang
Zhengrui Ma
Yang Feng

Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional encoder-decoder architecture and learn the generation and policy-making capabilities through complex dynamic programming techniques. Although LLMs excel at text generation, they face challenges in taking on the role of policy-makers through traditional training methods, limiting their exploration in simultaneous generation. To overcome these limitations, we propose a novel LLM-driven Simultaneous Generation (LSG) framework, which allows the off-the-shelf LLM to decide the generation timing and produce output concurrently. Specifically, LSG selects the generation policy that minimizes latency as the baseline policy. Referring to the baseline policy, LSG enables the LLM to devise an improved generation policy that better balances latency and generation quality, and writes generation results accordingly. Experiments on simultaneous translation and streaming automatic speech recognition tasks show that our method can achieve state-of-the-art performance utilizing the open-source LLMs and demonstrate practicality in real-world scenarios.

PDF Details DOI

JMLR Journal 2025 Journal Article

Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness

Ye Tian
Yuqi Gu
Yang Feng

Representation multi-task learning (MTL) has achieved tremendous success in practice. However, the theoretical understanding of these methods is still lacking. Most existing theoretical works focus on cases where all tasks share the same representation, and claim that MTL almost always improves performance. Nevertheless, as the number of tasks grows, assuming all tasks share the same representation is unrealistic. Furthermore, empirical findings often indicate that a shared representation does not necessarily improve single-task learning performance. In this paper, we aim to understand how to learn from tasks with similar but not exactly the same linear representations, while dealing with outlier tasks. Assuming a known intrinsic dimension, we propose a penalized empirical risk minimization method and a spectral method that are adaptive to the similarity structure and robust to outlier tasks. Both algorithms outperform single-task learning when representations across tasks are sufficiently similar and the proportion of outlier tasks is small. Moreover, they always perform at least as well as single-task learning, even when the representations are dissimilar. We provide information-theoretic lower bounds to demonstrate that both methods are nearly minimax optimal in a large regime, with the spectral method being optimal in the absence of outlier tasks. Additionally, we introduce a thresholding algorithm to adapt to an unknown intrinsic dimension. We conduct extensive numerical experiments to validate our theoretical findings. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2025. ( edit, beta )

IJCAI Conference 2025 Conference Paper

Modality-Fair Preference Optimization for Trustworthy MLLM Alignment

Songtao Jiang
Yan Zhang
Ruizhe Chen
Tianxiang Hu
Yeying Jin
Qinglin He
Yang Feng
Jian Wu

Multimodal large language models (MLLMs) have achieved remarkable success across various tasks. However, separate training of visual and textual encoders often results in a misalignment of the modality. Such misalignment may lead models to generate content that is absent from the input image, a phenomenon referred to as hallucination. These inaccuracies severely undermine the trustworthiness of MLLMs in real-world applications. Despite attempts to optimize text preferences to mitigate this issue, our initial investigation indicates that the trustworthiness of MLLMs remains inadequate. Specifically, these models tend to provide preferred answers even when the input image is heavily distorted. Analysis of visual token attention also indicates that the model focuses primarily on the surrounding context rather than the key object referenced in the question. These findings highlight a misalignment between the modalities, where answers inadequately leverage input images. Motivated by our findings, we propose Modality-Fair Preference Optimization (MFPO), which comprises three components: the construction of a multimodal preference dataset in which dispreferred images differ from originals solely in key regions; an image reward loss function encouraging the model to generate answers better aligned with the input images; and an easy-to-hard iterative alignment strategy to stabilize joint modality training. Extensive experiments on three trustworthiness benchmarks demonstrate that MFPO significantly enhances the trustworthiness of MLLMs. In particular, it enables the 7B models to attain trustworthiness levels on par with, or even surpass, those of the 13B, 34B, and larger models.

PDF Details DOI

EAAI Journal 2025 Journal Article

Solution and application of two-dimensional seismic wavefield evolution based on physics-informed neural networks

Zhihui Zhu
Zong Wang
Yang Feng
Weiqi Zheng

Physics-Informed Neural Networks (PINN) integrate partial differential equations, initial conditions, and boundary conditions into the loss function to predict the solutions of partial differential equations, and have already demonstrated their value in solving two-dimensional (2D) seismic wavefields. However, when dealing with wave problems involving boundary conditions, the added complexity of boundary conditions can lead to imbalanced convergence rates among different loss terms, which may affect both the efficiency and accuracy of the computations. Moreover, the need to retrain the model for different problems limits the flexibility of its application. Therefore, this paper introduces an adaptive weight balancing method and presents a 2D wave simulation based on Self-Adaptive PINN (SA-PINN). This method automatically adjusts the weights in the loss function, improving the solving performance. Additionally, to improve the computational efficiency of PINN in solving similar wave problems, a transfer learning strategy is adopted. By leveraging the similarities between the PINN models of related wave problems, this strategy enhances the generalization ability of PINN when dealing with variations in source location and medium wave speed. Numerical examples in semi-infinite domains and V-shaped valleys demonstrate that this method effectively achieves intelligent and efficient simulation of 2D seismic wavefields, providing a more efficient and intelligent solution for complex seismic wave problems.

NeurIPS Conference 2024 Conference Paper

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

Zhuofan Wen
Shangtong Gui
Yang Feng

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed.

PDF Details DOI

AAAI Conference 2024 Conference Paper

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling

Longxiang Liu
Xiuxing Li
Yang Feng

Task-oriented dialog systems have witnessed substantial progress due to conversational pre-training techniques. Yet, two significant challenges persist. First, most systems primarily utilize the latest turn's state label for the generator. This practice overlooks the comprehensive value of state labels in boosting the model's understanding for future generations. Second, an overreliance on generated policy often leads to error accumulation, resulting in suboptimal responses when adhering to incorrect actions. To combat these challenges, we propose turn-level multi-task objectives for the encoder. With the guidance of essential information from labeled intermediate states, we establish a more robust representation for both understanding and generation. For the decoder, we introduce an action tree-based scheduled sampling technique. Specifically, we model the hierarchical policy as trees and utilize the similarity between trees to sample negative policy based on scheduled sampling, hoping the model to generate invariant responses under perturbations. This method simulates potential pitfalls by sampling similar negative policy, bridging the gap between task-oriented dialog training and inference. Among methods without continual pre-training, our approach achieved state-of-the-art (SOTA) performance on the MultiWOZ dataset series and was also competitive with pre-trained SOTA methods.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Beyond MLE: Convex Learning for Text Generation

Chenze Shao
Zhengrui Ma
Min Zhang
Yang Feng

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at \url{https: //github. com/ictnlp/Convex-Learning}.

NeurIPS Conference 2023 Conference Paper

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

Qingkai Fang
Yan Zhou
Yang Feng

Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models. In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST. To better capture the complex distribution of the target speech, DASpeech adopts the two-pass architecture to decompose the generation process into two steps, where a linguistic decoder first generates the target text, and an acoustic decoder then generates the target speech based on the hidden states of the linguistic decoder. Specifically, we use the decoder of DA-Transformer as the linguistic decoder, and use FastSpeech 2 as the acoustic decoder. DA-Transformer models translations with a directed acyclic graph (DAG). To consider all potential paths in the DAG during training, we calculate the expected hidden states for each target token via dynamic programming, and feed them into the acoustic decoder to predict the target mel-spectrogram. During inference, we select the most probable path and take hidden states on that path as input to the acoustic decoder. Experiments on the CVSS Fr$\rightarrow$En benchmark demonstrate that DASpeech can achieve comparable or even better performance than the state-of-the-art S2ST model Translatotron 2, while preserving up to 18. 53$\times$ speedup compared to the autoregressive baseline. Compared with the previous non-autoregressive S2ST model, DASpeech does not rely on knowledge distillation and iterative decoding, achieving significant improvements in both translation quality and decoding speed. Furthermore, DASpeech shows the ability to preserve the speaker's voice of the source speech during translation.

NeurIPS Conference 2023 Conference Paper

Fast Model DeBias with Machine Unlearning

Ruizhe Chen
Jianfei Yang
Huimin Xiong
Jianhong Bai
Tianxiang Hu
Jin Hao
Yang Feng
Joey Tianyi Zhou

Recent discoveries have revealed that deep neural networks might behave in a biased manner in many real-world scenarios. For instance, deep networks trained on a large-scale face recognition dataset CelebA tend to predict blonde hair for females and black hair for males. Such biases not only jeopardize the robustness of models but also perpetuate and amplify social biases, which is especially concerning for automated decision-making processes in healthcare, recruitment, etc. , as they could exacerbate unfair economic and social inequalities among different groups. Existing debiasing methods suffer from high costs in bias labeling or model re-training, while also exhibiting a deficiency in terms of elucidating the origins of biases within the model. To this respect, we propose a fast model debiasing method (FMD) which offers an efficient approach to identify, evaluate and remove biases inherent in trained models. The FMD identifies biased attributes through an explicit counterfactual concept and quantifies the influence of data samples with influence functions. Moreover, we design a machine unlearning-based strategy to efficiently and effectively remove the bias in a trained model with a small counterfactual dataset. Experiments on the Colored MNIST, CelebA, and Adult Income datasets demonstrate that our method achieves superior or competing classification accuracies compared with state-of-the-art retraining-based methods while attaining significantly fewer biases and requiring much less debiasing cost. Notably, our method requires only a small external dataset and updating a minimal amount of model parameters, without the requirement of access to training data that may be too large or unavailable in practice.

NeurIPS Conference 2023 Conference Paper

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

Zikai Xiao
Zihan Chen
Songshang Liu
Hualiang Wang
Yang Feng
Jin Hao
Joey Tianyi Zhou
Jian Wu

Data privacy and long-tailed distribution are the norms rather than the exception in many real-world tasks. This paper investigates a federated long-tailed learning (Fed-LT) task in which each client holds a locally heterogeneous dataset; if the datasets can be globally aggregated, they jointly exhibit a long-tailed distribution. Under such a setting, existing federated optimization and/or centralized long-tailed learning methods hardly apply due to challenges in (a) characterizing the global long-tailed distribution under privacy constraints and (b) adjusting the local learning strategy to cope with the head-tail imbalance. In response, we propose a method termed $\texttt{Fed-GraB}$, comprised of a Self-adjusting Gradient Balancer (SGB) module that re-weights clients' gradients in a closed-loop manner, based on the feedback of global long-tailed distribution evaluated by a Direct Prior Analyzer (DPA) module. Using $\texttt{Fed-GraB}$, clients can effectively alleviate the distribution drift caused by data heterogeneity during the model training process and obtain a global model with better performance on the minority classes while maintaining the performance of the majority classes. Extensive experiments demonstrate that $\texttt{Fed-GraB}$ achieves state-of-the-art performance on representative datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist.

NeurIPS Conference 2023 Conference Paper

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

Yun Qu
Boyuan Wang
Jianzhun Shao
Yuhang Jiang
Chen Chen
Zhenbin Ye
Liu Linc
Yang Feng

The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications. However, existing datasets often fall short in their simplicity and lack of realism. To address this gap, we propose Hokoff, a comprehensive set of pre-collected datasets that covers both offline RL and offline MARL, accompanied by a robust framework, to facilitate further research. This data is derived from Honor of Kings, a recognized Multiplayer Online Battle Arena (MOBA) game known for its intricate nature, closely resembling real-life situations. Utilizing this framework, we benchmark a variety of offline RL and offline MARL algorithms. We also introduce a novel baseline algorithm tailored for the inherent hierarchical action space of the game. We reveal the incompetency of current offline RL approaches in handling task complexity, generalization and multi-task learning.

NeurIPS Conference 2023 Conference Paper

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

Shangtong Gui
Chenze Shao
Zhengrui Ma
Xishan Zhang
Yunji Chen
Yang Feng

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation. Code is publicly available at https: //github. com/ictnlp/PCFG-NAT.

AAAI Conference 2023 Conference Paper

Rephrasing the Reference for Non-autoregressive Machine Translation

Chenze Shao
Jinchao Zhang
Jie Zhou
Yang Feng

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when the NAT output is closer to other translations. In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output. As we train NAT based on the rephraser output rather than the reference sentence, the rephraser output should fit well with the NAT output and not deviate too far from the reference, which can be quantified as reward functions and optimized by reinforcement learning. Experiments on major WMT benchmarks and NAT baselines show that our approach consistently improves the translation quality of NAT. Specifically, our best variant achieves comparable performance to the autoregressive Transformer, while being 14.7 times more efficient in inference.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Towards Distribution-Agnostic Generalized Category Discovery

Jianhong Bai
Zuozhu Liu
Hualiang Wang
Ruizhe Chen
Lianrui Mu
Xiaomeng Li
Joey Tianyi Zhou
Yang Feng

Data imbalance and open-ended distribution are two intrinsic characteristics of the real visual world. Though encouraging progress has been made in tackling each challenge separately, few works dedicated to combining them towards real-world scenarios. While several previous works have focused on classifying close-set samples and detecting open-set samples during testing, it's still essential to be able to classify unknown subjects as human beings. In this paper, we formally define a more realistic task as distribution-agnostic generalized category discovery (DA-GCD): generating fine-grained predictions for both close- and open-set classes in a long-tailed open-world setting. To tackle the challenging problem, we propose a Self- Ba lanced Co -Advice co n trastive framework (BaCon), which consists of a contrastive-learning branch and a pseudo-labeling branch, working collaboratively to provide interactive supervision to resolve the DA-GCD task. In particular, the contrastive-learning branch provides reliable distribution estimation to regularize the predictions of the pseudo-labeling branch, which in turn guides contrastive learning through self-balanced knowledge transfer and a proposed novel contrastive loss. We compare BaCon with state-of-the-art methods from two closely related fields: imbalanced semi-supervised learning and generalized category discovery. The effectiveness of BaCon is demonstrated with superior performance over all baselines and comprehensive analysis across various datasets. Our code is publicly available.

NeurIPS Conference 2023 Conference Paper

Unified Segment-to-Segment Framework for Simultaneous Sequence Generation

Shaolei Zhang
Yang Feng

Simultaneous sequence generation is a pivotal task for real-time scenarios, such as streaming speech recognition, simultaneous machine translation and simultaneous speech translation, where the target sequence is generated while receiving the source sequence. The crux of achieving high-quality generation with low latency lies in identifying the optimal moments for generating, accomplished by learning a mapping between the source and target sequences. However, existing methods often rely on task-specific heuristics for different sequence types, limiting the model’s capacity to adaptively learn the source-target mapping and hindering the exploration of multi-task learning for various simultaneous tasks. In this paper, we propose a unified segment-to-segment framework (Seg2Seg) for simultaneous sequence generation, which learns the mapping in an adaptive and unified manner. During the process of simultaneous generation, the model alternates between waiting for a source segment and generating a target segment, making the segment serve as the natural bridge between the source and target. To accomplish this, Seg2Seg introduces a latent segment as the pivot between source to target and explores all potential source-target mappings via the proposed expectation training, thereby learning the optimal moments for generating. Experiments on multiple simultaneous generation tasks demonstrate that Seg2Seg achieves state-of-the-art performance and exhibits better generality across various tasks.

NeurIPS Conference 2022 Conference Paper

Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation

Chenze Shao
Yang Feng

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent alignment models relax the explicit alignment by marginalizing out all monotonic latent alignments with the CTC loss. However, they cannot handle non-monotonic alignments, which is non-negligible as there is typically global word reordering in machine translation. In this work, we explore non-monotonic latent alignments for NAT. We extend the alignment space to non-monotonic alignments to allow for the global word reordering and further consider all alignments that overlap with the target sentence. We non-monotonically match the alignments to the target sentence and train the latent alignment model to maximize the F1 score of non-monotonic matching. Extensive experiments on major WMT benchmarks show that our method substantially improves the translation performance of CTC-based models. Our best model achieves 30. 06 BLEU on WMT14 En-De with only one-iteration decoding, closing the gap between non-autoregressive and autoregressive models.

ICLR Conference 2022 Conference Paper

Relational Surrogate Loss Learning

Tao Huang 0020
Zekang Li
Hua Lu 0017
Yong Shan
Shusheng Yang
Yang Feng
Fei Wang 0032
Shan You

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the surrogate loss learning, where a deep neural network is employed to approximate the evaluation metrics. Instead of pursuing an exact recovery of the evaluation metric through a deep neural network, we are reminded of the purpose of the existence of these evaluation metrics, which is to distinguish whether one model is better or worse than another. In this paper, we show that directly maintaining the relation of models between surrogate losses and metrics suffices, and propose a rank correlation-based optimization method to maximize this relation and learn surrogate losses. Compared to previous works, our method is much easier to optimize and enjoys significant efficiency and performance gains. Extensive experiments show that our method achieves improvements on various tasks including image classification and neural machine translation, and even outperforms state-of-the-art methods on human pose estimation and machine reading comprehension tasks. Code is available at: https://github.com/hunto/ReLoss.

AAAI Conference 2021 Conference Paper

Future-Guided Incremental Transformer for Simultaneous Translation

Shaolei Zhang
Yang Feng
Liangyou Li

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two weaknesses: low training speed caused by the recalculation of hidden states and lack of future source information to guide training. For the low training speed, we propose an incremental Transformer with an average embedding layer (AEL) to accelerate the speed of calculation of the hidden states during training. For future-guided training, we propose a conventional Transformer as the teacher of the incremental Transformer, and try to invisibly embed some future information in the model through knowledge distillation. We conducted experiments on Chinese-English and German- English simultaneous translation tasks and compared with the wait-k policy to evaluate the proposed method. Our method can effectively increase the training speed by about 28 times on average at different k and implicitly embed some predictive abilities in the model, achieving better translation quality than wait-k baseline.

JMLR Journal 2021 Journal Article

RaSE: Random Subspace Ensemble Classification

Ye Tian
Yang Feng

We propose a flexible ensemble classification framework, Random Subspace Ensemble (RaSE), for sparse classification. In the RaSE algorithm, we aggregate many weak learners, where each weak learner is a base classifier trained in a subspace optimally selected from a collection of random subspaces. To conduct subspace selection, we propose a new criterion, ratio information criterion (RIC), based on weighted Kullback-Leibler divergence. The theoretical analysis includes the risk and Monte-Carlo variance of the RaSE classifier, establishing the screening consistency and weak consistency of RIC, and providing an upper bound for the misclassification rate of the RaSE classifier. In addition, we show that in a high-dimensional framework, the number of random subspaces needs to be very large to guarantee that a subspace covering signals is selected. Therefore, we propose an iterative version of the RaSE algorithm and prove that under some specific conditions, a smaller number of generated random subspaces are needed to find a desirable subspace through iteration. An array of simulations under various models and real-data applications demonstrate the effectiveness and robustness of the RaSE classifier and its iterative version in terms of low misclassification rate and accurate feature ranking. The RaSE algorithm is implemented in the R package RaSEn on CRAN. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

IJCAI Conference 2020 Conference Paper

Bridging the Gap between Training and Inference for Neural Machine Translation (Extended Abstract)

Wen Zhang
Yang Feng
Qun Liu

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context leads to error accumulation among the translation. Furthermore, word-level training requires strict matching between the generated sequence and the ground truth sequence which leads to overcorrection over different but reasonable translations. In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence during training. Experimental results on NIST Chinese->English and WMT2014 English->German translation tasks demonstrate that our method can achieve significant improvements on multiple data sets compared to strong baselines.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation

Chenze Shao
Jinchao Zhang
Yang Feng
Fandong Meng
Jie Zhou

Non-Autoregressive Neural Machine Translation (NAT) achieves signiﬁcant decoding speedup through generating target words independently and simultaneously. However, in the context of non-autoregressive translation, the word-level cross-entropy loss cannot model the target-side sequential dependency properly, leading to its weak correlation with the translation quality. As a result, NAT tends to generate in- ﬂuent translations with over-translation and under-translation errors. In this paper, we propose to train NAT to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The bag-of-ngrams training objective is differentiable and can be efﬁciently calculated, which encourages NAT to capture the target-side sequential dependency and correlates well with the translation quality. We validate our approach on three translation tasks and show that our approach largely outperforms the NAT baseline by about 5. 0 BLEU scores on WMT14 En↔De and about 2. 5 BLEU scores on WMT16 En↔Ro.

AAAI Conference 2020 Conference Paper

Modeling Fluency and Faithfulness for Diverse Neural Machine Translation

Yang Feng
Wanying Xie
Shuhao Gu
Chenze Shao
Wen Zhang
Zhengxin Yang
Dong Yu

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution. However, the strategy casts all the portion of the distribution to the ground truth word and ignores other words in the target vocabulary even when the ground truth word cannot dominate the distribution. To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. The evaluation module accesses each prediction from the perspectives of ﬂuency and faithfulness to encourage the model to generate the word which has a ﬂuent connection with its past and future translation and meanwhile tends to form a translation equivalent in meaning to the source. The experiments on multiple translation tasks show that our method can achieve signiﬁcant improvements over strong baselines.

JMLR Journal 2020 Journal Article

Neyman-Pearson classification: parametrics and sample size requirement

Xin Tong
Lucy Xia
Jiacheng Wang
Yang Feng

The Neyman-Pearson (NP) paradigm in binary classification seeks classifiers that achieve a minimal type II error while enforcing the prioritized type I error controlled under some user-specified level $\alpha$. This paradigm serves naturally in applications such as severe disease diagnosis and spam detection, where people have clear priorities among the two error types. Recently, Tong, Feng, and Li (2018) proposed a nonparametric umbrella algorithm that adapts all scoring-type classification methods (e.g., logistic regression, support vector machines, random forest) to respect the given type I error (i.e., conditional probability of classifying a class $0$ observation as class $1$ under the 0-1 coding) upper bound $\alpha$ with high probability, without specific distributional assumptions on the features and the responses. Universal the umbrella algorithm is, it demands an explicit minimum sample size requirement on class $0$, which is often the more scarce class, such as in rare disease diagnosis applications. In this work, we employ the parametric linear discriminant analysis (LDA) model and propose a new parametric thresholding algorithm, which does not need the minimum sample size requirements on class $0$ observations and thus is suitable for small sample applications such as rare disease diagnosis. Leveraging both the existing nonparametric and the newly proposed parametric thresholding rules, we propose four LDA-based NP classifiers, for both low- and high-dimensional settings. On the theoretical front, we prove NP oracle inequalities for one proposed classifier, where the rate for excess type II error benefits from the explicit parametric model assumption. Furthermore, as NP classifiers involve a sample splitting step of class $0$ observations, we construct a new adaptive sample splitting scheme that can be applied universally to NP classifiers, and this adaptive strategy reduces the type II error of these classifiers. The proposed NP classifiers are implemented in the R package nproc. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2020. ( edit, beta )

AAAI Conference 2019 Conference Paper

Multi-Winner Contests for Strategic Diffusion in Social Networks

Wen Shen
Yang Feng
Cristina V. Lopes

Strategic diffusion encourages participants to take active roles in promoting stakeholders’ agendas by rewarding successful referrals. As social media continues to transform the way people communicate, strategic diffusion has become a powerful tool for stakeholders to influence people’s decisions or behaviors for desired objectives. Existing reward mechanisms for strategic diffusion are usually either vulnerable to falsename attacks or not individually rational for participants that have made successful referrals. Here, we introduce a novel multi-winner contests (MWC) mechanism for strategic diffusion in social networks. The MWC mechanism satisfies several desirable properties, including false-name-proofness, individual rationality, budget constraint, monotonicity, and subgraph constraint. Numerical experiments on four real-world social network datasets demonstrate that stakeholders can significantly boost participants’ aggregated efforts with proper design of competitions. Our work sheds light on how to design manipulation-resistant mechanisms with appropriate contests.

JMLR Journal 2016 Journal Article

Neyman-Pearson Classification under High-Dimensional Settings

Anqi Zhao
Yang Feng
Lie Wang
Xin Tong

Most existing binary classification methods target on the optimization of the overall classification risk and may fail to serve some real-world applications such as cancer diagnosis, where users are more concerned with the risk of misclassifying one specific class than the other. Neyman-Pearson (NP) paradigm was introduced in this context as a novel statistical framework for handling asymmetric type I/II error priorities. It seeks classifiers with a minimal type II error and a constrained type I error under a user specified level. This article is the first attempt to construct classifiers with guaranteed theoretical performance under the NP paradigm in high-dimensional settings. Based on the fundamental Neyman-Pearson Lemma, we used a plug-in approach to construct NP-type classifiers for Naive Bayes models. The proposed classifiers satisfy the NP oracle inequalities, which are natural NP paradigm counterparts of the oracle inequalities in classical binary classification. Besides their desirable theoretical properties, we also demonstrated their numerical advantages in prioritized error control via both simulation and real data studies. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )