Arrow Research search

Author name cluster

Wei Cheng

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.

43 papers
2 author rows

Possible papers

43

AAAI Conference 2026 Conference Paper

SkillGen: Learning Domain Skills for In-Context Sequential Decision Making

  • Ruomeng Ding
  • Wei Cheng
  • Minglai Shao
  • Chen Zhao

Large language models (LLMs) are increasingly applied to sequential decision-making through in-context learning (ICL), yet their effectiveness is highly sensitive to prompt quality. Effective prompts should meet three principles: focus on decision-critical information, provide step-level granularity, and minimize reliance on expert annotations through label efficiency. However, existing ICL methods often fail to satisfy all three criteria simultaneously. Motivated by these challenges, we introduce SkillGen, a skill-based ICL framework for structured sequential reasoning. It constructs an action-centric, domain-level graph from sampled trajectories, identifies high-utility actions via temporal-difference credit assignment, and retrieves step-wise skills to generate fine-grained, context-aware prompts. We further present a theoretical analysis showing that focusing on high-utility segments supports task identifiability and informs more effective ICL prompt design. Experiments on ALFWorld, BabyAI, and ScienceWorld, using both open-source and proprietary LLMs, show that SkillGen achieves consistent gains, improving progress rate by 5.9%–16.5% on average across models.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers

  • pengtao chen
  • Xianfang Zeng
  • Maosen Zhao
  • Mingzhu Shen
  • Wei Cheng
  • Gang Yu
  • Tao Chen

While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency. Through detailed analysis of attention maps in Video Diffusion Transformer (vDiT), we identify three recurring sparsity patterns: diagonal, multi-diagonal, and vertical-stripe structures. And even 3-6% attention heads can be skipped. Crucially, these patterns exhibit strong layer-depth and head-position correlations but show limited dependence on the input content. Leveraging these findings, we propose Sparse-vDiT, a sparsity acceleration framework for vDiT comprising: 1) Pattern-optimized sparse kernels that replace dense attention with computationally efficient implementations for each identified sparsity pattern. 2) An offline sparse diffusion search algorithm that selects the optimal sparse computation strategy per layer and head via hardware-aware cost modeling. After determining the optimal configuration, we fuse heads within the same layer that share the same attention strategy, enhancing inference efficiency. Integrated into state-of-the-art vDiT models (CogVideoX1.5, HunyuanVideo, and Wan2.1), Sparse-vDiT achieves 2.09×, 2.38×, and 1.67× theoretical FLOP reduction, and actual inference speedups of 1.76×, 1.85×, and 1.58×, respectively, while maintaining high visual fidelity, with PSNR values reaching 24.13, 27.09, and 22.59. Our work demonstrates that latent structural sparsity in vDiTs can be systematically exploited for long video synthesis.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

DISC: Dynamic Decomposition Improves LLM Inference Scaling

  • Jonathan Li
  • Wei Cheng
  • Benjamin Riviere
  • Yue Wu
  • Masafumi Oyamada
  • Mengdi Wang
  • Yisong Yue
  • Santiago Paternain

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually designed based on domain knowledge. We propose dynamic decomposition, a method that adaptively and automatically partitions solution and reasoning traces into manageable steps during inference. By more effectively allocating compute -- particularly through subdividing challenging steps and prioritizing their sampling -- dynamic decomposition significantly improves inference efficiency. Experiments on benchmarks such as APPS, MATH, and LiveCodeBench demonstrate that dynamic decomposition outperforms static approaches, including token-level, sentence-level, and single-step decompositions, reducing the pass@10 error rate by 5. 0%, 6. 7%, and 10. 5% respectively. These findings highlight the potential of dynamic decomposition to improve a wide range of inference scaling techniques.

PDF Details

NeurIPS Conference 2025 Conference Paper

FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding

  • Chongjun Tu
  • Lin Zhang
  • pengtao chen
  • Peng Ye
  • Xianfang Zeng
  • Wei Cheng
  • Gang Yu
  • Tao Chen

Multimodal Large Language Models (MLLMs) have shown impressive video content understanding capabilities but struggle with fine-grained motion comprehension. To comprehensively assess the motion understanding ability of existing MLLMs, we introduce FAVOR-Bench, which comprises 1, 776 videos from both ego-centric and third-person perspectives and enables assessment through both close-ended and open-ended tasks. For close-ended evaluation, we carefully design 8, 184 multiple-choice question-answer pairs spanning six distinct sub-tasks. For open-ended evaluation, we employ the GPT-assisted evaluation and develop a novel cost-efficient LLM-free assessment method, where the latter can enhance benchmarking interpretability and accessibility. Comprehensive experiments with21 state-of-the-art MLLMs reveal significant limitations in their ability to comprehend and describe detailed temporal dynamics in video motions. To alleviate this limitation, we further build FAVOR-Train, a dataset of 17, 152 videos with fine-grained motion annotations. Finetuning Qwen2. 5-VL on FAVOR-Train yields consistent improvements on motion-related tasks across TVBench, MotionBenchand our FAVOR-Bench. Our assessment results demonstrate that the proposed FAVOR-Bench and FAVOR-Train provide valuable tools for the community to develop more powerful video understanding models.

PDF Details

IJCAI Conference 2025 Conference Paper

Harnessing Vision Models for Time Series Analysis: A Survey

  • Jingchao Ni
  • Ziming Zhao
  • ChengAo Shen
  • Hanghang Tong
  • Dongjin Song
  • Wei Cheng
  • Dongsheng Luo
  • Haifeng Chen

Time series analysis has evolved from traditional autoregressive models to deep learning, Transformers, and Large Language Models (LLMs). While vision models have also been explored along the way, their contributions are less recognized due to the predominance of sequence modeling. However, challenges such as the mismatch between continuous time series and LLMs’ discrete token space, and the difficulty in capturing multivariate correlations, have led to growing interest in Large Vision Models (LVMs) and Vision-Language Models (VLMs). This survey highlights the advantages of vision models over LLMs in time series analysis, offering a comprehensive dual-view taxonomy that answers key research questions like how to encode time series as images and how to model imaged time series. Additionally, we address pre- and post-processing challenges in this framework and outline future directions for advancing the field.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

  • Cong Zeng
  • Shengkun Tang
  • Yuanzhou Chen
  • Zhiqiang Shen
  • Wenchao Yu
  • Xujiang Zhao
  • Haifeng Chen
  • Wei Cheng

The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication. This trend has heightened the need for reliable detection methods to distinguish between human-authored and machine-generated content. Existing approaches both zero-shot methods and supervised classifiers largely conceptualize this task as a binary classification problem, often leading to poor generalization across domains and models. In this paper, we argue that such a binary formulation fundamentally mischaracterizes the detection task by assuming a coherent representation of human-written texts. In reality, human texts do not constitute a unified distribution, and their diversity cannot be effectively captured through limited sampling. This causes previous classifiers to memorize observed OOD characteristics rather than learn the essence of `non-ID' behavior, limiting generalization to unseen human-authored inputs. Based on this observation, we propose reframing the detection task as an out-of-distribution (OOD) detection problem, treating human-written texts as distributional outliers while machine-generated texts are in-distribution (ID) samples. To this end, we develop a detection framework using one-class learning method including DeepSVDD and HRN, and score-based learning techniques such as energy-based method, enabling robust and generalizable performance. Extensive experiments across multiple datasets validate the effectiveness of our OOD-based approach. Specifically, the OOD-based method achieves 98. 3\% AUROC and AUPR with only 8. 9\% FPR95 on DeepFake dataset. Moreover, we test our detection framework on multilingual, attacked, and unseen-model and -domain text settings, demonstrating the robustness and generalizability of our framework. Code will be released openly and also available in the supplementary materials.

PDF Details

NeurIPS Conference 2025 Conference Paper

Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

  • ChengAo Shen
  • Wenchao Yu
  • Ziming Zhao
  • Dongjin Song
  • Wei Cheng
  • Haifeng Chen
  • Jingchao Ni

Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMVs can reveal complementary patterns and enable the use of powerful pre-trained large models, such as large vision models (LVMs), for long-term time series forecasting (LTSF). However, as we identified in this work, the state-of-the-art (SOTA) LVM-based forecaster poses an inductive bias towards "forecasting periods". To harness this bias, we propose DMMV, a novel decomposition-based multi-modal view framework that leverages trend-seasonal decomposition and a novel backcast-residual based adaptive decomposition to integrate MMVs for LTSF. Comparative evaluations against 14 SOTA models across diverse datasets show that DMMV outperforms single-view and existing multi-modal baselines, achieving the best mean squared error (MSE) on 6 out of 8 benchmark datasets. The code for this paper is available at: https: //github. com/D2I-Group/dmmv.

PDF Details

NeurIPS Conference 2025 Conference Paper

OmniSVG: A Unified Scalable Vector Graphics Generation Model

  • Yiying Yang
  • Wei Cheng
  • Sijin Chen
  • Xianfang Zeng
  • Fukun Yin
  • Jiaxu Zhang
  • Liao Wang
  • Gang Yu

Scalable Vector Graphics (SVG) is an important image format widely adopted in graphic design because of their resolution independence and editability. The study of generating high-quality SVG has continuously drawn attention from both designers and researchers in the AIGC community. However, existing methods either produces unstructured outputs with huge computational cost or is limited to generating monochrome icons of over-simplified structures. To produce high-quality and complex SVG, we propose OmniSVG, a unified framework that leverages pre-trained Vision-Language Models (VLMs) for end-to-end multimodal SVG generation. By parameterizing SVG commands and coordinates into discrete tokens, OmniSVG decouples structural logic from low-level geometry for efficient training while maintaining the expressiveness of complex SVG structure. To further advance the development of SVG synthesis, we introduce MMSVG-2M, a multimodal dataset with two million richly annotated SVG assets, along with a standardized evaluation protocol for conditional SVG generation tasks. Extensive experiments show that OmniSVG outperforms existing methods and demonstrates its potential for integration into professional SVG design workflows.

PDF Details

NeurIPS Conference 2025 Conference Paper

OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation

  • Jingjing Chang
  • Yixiao Fang
  • Peng Xing
  • Shuhan Wu
  • Wei Cheng
  • Rui Wang
  • Xianfang Zeng
  • Gang Yu

Text-to-image (T2I) models have garnered significant attention for generating high-quality images aligned with text prompts. However, rapid T2I model advancements reveal limitations in early benchmarks, lacking comprehensive evaluations, especially for text rendering and style. Notably, recent state-of-the-art models, with their rich knowledge modeling capabilities, show potential in reasoning-driven image generation, yet existing evaluation systems have not adequately addressed this frontier. To systematically address these gaps, we introduce $\textbf{OneIG-Bench}$, a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models across multiple dimensions, including subject-element alignment, text rendering precision, reasoning-generated content, stylization, and diversity. By structuring the evaluation, this benchmark enables in-depth analysis of model performance, helping researchers and practitioners pinpoint strengths and bottlenecks in the full pipeline of image generation. Our codebase and dataset are now publicly available to facilitate reproducible evaluation studies and cross-model comparisons within the T2I research community.

PDF Details

NeurIPS Conference 2025 Conference Paper

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search

  • Dong Li
  • Xujiang Zhao
  • Linlin Yu
  • Yanchi Liu
  • Wei Cheng
  • Zhengzhang Chen
  • Zhong Chen
  • Feng Chen

Large Language Models (LLMs) offer promising capabilities for tackling complex reasoning tasks, including optimization problems. However, existing methods either rely on prompt engineering, which leads to poor generalization across problem types, or require costly supervised training. We introduce SolverLLM, a training-free framework that leverages test-time scaling to solve diverse optimization problems. Rather than solving directly, SolverLLM generates mathematical formulations and translates them into solver-ready code, guided by a novel Monte Carlo Tree Search (MCTS) strategy. To enhance the search process, we modify classical MCTS with (1) dynamic expansion for adaptive formulation generation, (2) prompt backpropagation to guide exploration via outcome-driven feedback, and (3) uncertainty backpropagation to incorporate reward reliability into decision-making. Experiments on six standard benchmark datasets demonstrate that SolverLLM outperforms both prompt-based and learning-based baselines, achieving strong generalization without additional training.

PDF Details

ICLR Conference 2025 Conference Paper

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

  • Jonathan Light
  • Min Cai
  • Weiqin Chen 0003
  • Guanzhi Wang
  • Xiusi Chen
  • Wei Cheng
  • Yisong Yue
  • Ziniu Hu

Traditional reinforcement learning and planning require a lot of data and training to develop effective strategies. On the other hand, large language models (LLMs) can generalize well and perform tasks without prior training but struggle with complex planning and decision-making. We introduce **STRATEGIST**, a new approach that combines the strengths of both methods. It uses LLMs to generate and update high-level strategies in text form, while a Monte Carlo Tree Search (MCTS) algorithm refines and executes them. STRATEGIST is a general framework that optimizes strategies through self-play simulations without requiring any training data. We test STRATEGIST in competitive, multi-turn games with partial information, such as **Game of Pure Strategy (GOPS)** and **The Resistance: Avalon**, a multi-agent hidden-identity discussion game. Our results show that STRATEGIST-based agents outperform traditional reinforcement learning models, other LLM-based methods, and existing LLM agents while achieving performance levels comparable to human players.

Details

AAAI Conference 2025 Conference Paper

TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents

  • Geon Lee
  • Wenchao Yu
  • Kijung Shin
  • Wei Cheng
  • Haifeng Chen

Time series data is essential in various applications, including climate modeling, healthcare monitoring, and financial analytics. Understanding the contextual information associated with real-world time series data is often essential for accurate and reliable event predictions. In this paper, we introduce TimeCAP, a time-series processing framework that creatively employs Large Language Models (LLMs) as contextualizers of time series data, extending their typical usage as predictors. TimeCAP incorporates two independent LLM agents: one generates a textual summary capturing the context of the time series, while the other uses this enriched summary to make more informed predictions. In addition, TimeCAP employs a multi-modal encoder that synergizes with the LLM agents, enhancing predictive performance through mutual augmentation of inputs with in-context examples. Experimental results on real-world datasets demonstrate that TimeCAP outperforms state-of-the-art methods for time series event prediction, including those utilizing LLMs as predictors, achieving an average improvement of 28.75% in F1 score.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop

  • Yushan Jiang
  • Wenchao Yu
  • Geon Lee
  • Dongjin Song
  • Kijung Shin
  • Wei Cheng
  • Yanchi Liu
  • Haifeng Chen

Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual signals present in auxiliary modalities. To bridge this gap, we introduce TimeXL, a multi-modal prediction framework that integrates a prototype-based time series encoder with three collaborating Large Language Models (LLMs) to deliver more accurate predictions and interpretable explanations. First, a multi-modal prototype-based encoder processes both time series and textual inputs to generate preliminary forecasts alongside case-based rationales. These outputs then feed into a prediction LLM, which refines the forecasts by reasoning over the encoder's predictions and explanations. Next, a reflection LLM compares the predicted values against the ground truth, identifying textual inconsistencies or noise. Guided by this feedback, a refinement LLM iteratively enhances text quality and triggers encoder retraining. This closed-loop workflow---prediction, critique (reflect), and refinement---continuously boosts the framework's performance and interpretability. Empirical evaluations on four real-world datasets demonstrate that TimeXL achieves up to 8. 9\% improvement in AUC and produces human-centric, multi-modal explanations, highlighting the power of LLM-driven reasoning for time series prediction.

PDF Details

NeurIPS Conference 2024 Conference Paper

DALD: Improving Logits-based Detector without Logits from Black-box LLMs

  • Cong Zeng
  • Shengkun Tang
  • Xianjun Yang
  • Yuanzhou Chen
  • Yiyou Sun
  • Zhiqiang Xu
  • Yao Li
  • Haifeng Chen

The advent of Large Language Models (LLMs) has revolutionized text generation, producing outputs that closely mimic human writing. This blurring of lines between machine- and human-written text presents new challenges in distinguishing one from the other – a task further complicated by the frequent updates and closed nature of leading proprietary LLMs. Traditional logits-based detection methods leverage surrogate models for identifying LLM-generated content when the exact logits are unavailable from black-box LLMs. However, these methods grapple with the misalignment between the distributions of the surrogate and the often undisclosed target models, leading to performance degradation, particularly with the introduction of new, closed-source models. Furthermore, while current methodologies are generally effective when the source model is identified, they falter in scenarios where the model version remains unknown, or the test set comprises outputs from various source models. To address these limitations, we present \textbf{D}istribution-\textbf{A}ligned \textbf{L}LMs \textbf{D}etection (DALD), an innovative framework that redefines the state-of-the-art performance in black-box text detection even without logits from source LLMs. DALD is designed to align the surrogate model's distribution with that of unknown target LLMs, ensuring enhanced detection capability and resilience against rapid model iterations with minimal training investment. By leveraging corpus samples from publicly accessible outputs of advanced models such as ChatGPT, GPT-4 and Claude-3, DALD fine-tunes surrogate models to synchronize with unknown source model distributions effectively. Our approach achieves SOTA performance in black-box settings on different advanced closed-source and open-source models. The versatility of our method enriches widely adopted zero-shot detection frameworks (DetectGPT, DNA-GPT, Fast-DetectGPT) with a `plug-and-play' enhancement feature. Extensive experiments validate that our methodology reliably secures high detection precision for LLM-generated text and effectively detects text from diverse model origins through a singular detector. Our method is also robust under the revised text attack and non-English texts.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

MeshXL: Neural Coordinate Field for Generative 3D Foundation Models

  • Sijin Chen
  • Xin Chen
  • Anqi Pang
  • Xianfang Zeng
  • Wei Cheng
  • Yijun Fu
  • Fukun Yin
  • Zhibin Wang

The polygon mesh representation of 3D data exhibits great flexibility, fast rendering speed, and storage efficiency, which is widely preferred in various applications. However, given its unstructured graph representation, the direct generation of high-fidelity 3D meshes is challenging. Fortunately, with a pre-defined ordering strategy, 3D meshes can be represented as sequences, and the generation process can be seamlessly treated as an auto-regressive problem. In this paper, we validate Neural Coordinate Field (NeurCF), an explicit coordinate representation with implicit neural embeddings, is a simple-yet-effective representation for large-scale sequential mesh modeling. After that, we present MeshXL, a family of generative pre-trained auto-regressive models that addresses 3D mesh generation with modern large language model approaches. Extensive experiments show that MeshXL is able to generate high-quality 3D meshes, and can also serve as foundation models for various down-stream applications.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Protecting Your LLMs with Information Bottleneck

  • Zichuan Liu
  • Zefan Wang
  • Linjie Xu
  • Jinyu Wang
  • Lei Song
  • Tianchun Wang
  • Chunlin Chen
  • Wei Cheng

The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to ethically align LLMs, these are often fragile and can be circumvented by jailbreaking attacks through optimized or manual adversarial prompts. To address this, we introduce the Information Bottleneck Protector (IBProtector), a defense mechanism grounded in the information bottleneck principle, and we modify the objective to avoid trivial solutions. The IBProtector selectively compresses and perturbs prompts, facilitated by a lightweight and trainable extractor, preserving only essential information for the target LLMs to respond with the expected answer. Moreover, we further consider a situation where the gradient is not visible to be compatible with any LLM. Our empirical evaluations show that IBProtector outperforms current defense methods in mitigating jailbreak attempts, without overly affecting response quality or inference speed. Its effectiveness and adaptability across various attack methods and target LLMs underscore the potential of IBProtector as a novel, transferable defense that bolsters the security of LLMs without requiring modifications to the underlying models.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Hierarchical Gaussian Mixture based Task Generative Model for Robust Meta-Learning

  • Yizhou Zhang
  • Jingchao Ni
  • Wei Cheng
  • Zhengzhang Chen
  • Liang Tong
  • Haifeng Chen
  • Yan Liu

Meta-learning enables quick adaptation of machine learning models to new tasks with limited data. While tasks could come from varying distributions in reality, most of the existing meta-learning methods consider both training and testing tasks as from the same uni-component distribution, overlooking two critical needs of a practical solution: (1) the various sources of tasks may compose a multi-component mixture distribution, and (2) novel tasks may come from a distribution that is unseen during meta-training. In this paper, we demonstrate these two challenges can be solved jointly by modeling the density of task instances. We develop a meta-training framework underlain by a novel Hierarchical Gaussian Mixture based Task Generative Model (HTGM). HTGM extends the widely used empirical process of sampling tasks to a theoretical model, which learns task embeddings, fits the mixture distribution of tasks, and enables density-based scoring of novel tasks. The framework is agnostic to the encoder and scales well with large backbone networks. The model parameters are learned end-to-end by maximum likelihood estimation via an Expectation-Maximization (EM) algorithm. Extensive experiments on benchmark datasets indicate the effectiveness of our method for both sample classification and novel task detection.

PDF Details

NeurIPS Conference 2023 Conference Paper

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

  • Dongwei Pan
  • Long Zhuo
  • Jingtan Piao
  • Huiwen Luo
  • Wei Cheng
  • Yuxin Wang
  • Siming Fan
  • Shengqi Liu

Synthesizing high-fidelity head avatars is a central problem for computer vision and graphics. While head avatar synthesis algorithms have advanced rapidly, the best ones still face great obstacles in real-world scenarios. One of the vital causes is the inadequate datasets -- 1) current public datasets can only support researchers to explore high-fidelity head avatars in one or two task directions; 2) these datasets usually contain digital head assets with limited data volume, and narrow distribution over different attributes, such as expressions, ages, and accessories. In this paper, we present RenderMe-360, a comprehensive 4D human head dataset to drive advance in head avatar algorithms across different scenarios. It contains massive data assets, with 243+ million complete head frames and over 800k video sequences from 500 different identities captured by multi-view cameras at 30 FPS. It is a large-scale digital library for head avatars with three key attributes: 1) High Fidelity: all subjects are captured in 360 degrees via 60 synchronized, high-resolution 2K cameras. 2) High Diversity: The collected subjects vary from different ages, eras, ethnicities, and cultures, providing abundant materials with distinctive styles in appearance and geometry. Moreover, each subject is asked to perform various dynamic motions, such as expressions and head rotations, which further extend the richness of assets. 3) Rich Annotations: the dataset provides annotations with different granularities: cameras' parameters, background matting, scan, 2D/3D facial landmarks, FLAME fitting, and text description. Based on the dataset, we build a comprehensive benchmark for head avatar research, with 16 state-of-the-art methods performed on five main tasks: novel view synthesis, novel expression synthesis, hair rendering, hair editing, and talking head generation. Our experiments uncover the strengths and flaws of state-of-the-art methods. RenderMe-360 opens the door for future exploration in modern head avatars. All of the data, code, and models will be publicly available at https: //renderme-360. github. io/.

PDF Details

AAAI Conference 2023 Conference Paper

Time Series Contrastive Learning with Information-Aware Augmentations

  • Dongsheng Luo
  • Wei Cheng
  • Yingheng Wang
  • Dongkuan Xu
  • Jingchao Ni
  • Wenchao Yu
  • Xuchao Zhang
  • Yanchi Liu

Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples, such that an encoder can be trained to learn robust and discriminative representations. Unlike image and language domains where "desired'' augmented samples can be generated with the rule of thumb guided by prefabricated human priors, the ad-hoc manual selection of time series augmentations is hindered by their diverse and human-unrecognizable temporal structures. How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question. In this work, we address the problem by encouraging both high fidelity and variety based on information theory. A theoretical analysis leads to the criteria for selecting feasible data augmentations. On top of that, we propose a new contrastive learning approach with information-aware augmentations, InfoTS, that adaptively selects optimal augmentations for time series representation learning. Experiments on various datasets show highly competitive performance with up to a 12.0% reduction in MSE on forecasting tasks and up to 3.7% relative improvement in accuracy on classification tasks over the leading baselines.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph

  • Liyan Xu
  • Xuchao Zhang
  • Bo Zong
  • Yanchi Liu
  • Wei Cheng
  • Jingchao Ni
  • Haifeng Chen
  • Liang Zhao

We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within each sentence. While previous work has demonstrated effective syntax-guided MRC models, we propose to adopt the inter-sentence syntactic relations, in addition to the rudimentary intra-sentence relations, to further utilize the syntactic dependencies in the multi-sentence input of the MRC task. In our approach, we build the Inter-Sentence Dependency Graph (ISDG) connecting dependency trees to form global syntactic relations across sentences. We then propose the ISDG encoder that encodes the global dependency graph, addressing the inter-sentence relations via both one-hop and multi-hop dependency paths explicitly. Experiments on three multilingual MRC datasets (XQuAD, MLQA, TyDiQA-GoldP) show that our encoder that is only trained on English is able to improve the zero-shot performance on all 14 test sets covering 8 languages, with up to 3. 8 F1 / 5. 2 EM improvement on-average, and 5. 2 F1 / 11. 2 EM on certain languages. Further analysis shows the improvement can be attributed to the attention on the cross-linguistically consistent syntactic path. Our code is available at https: //github. com/lxucs/ multilingual-mrc-isdg.

PDF Details

AAAI Conference 2021 Conference Paper

Adaptive Prior-Dependent Correction Enhanced Reinforcement Learning for Natural Language Generation

  • Wei Cheng
  • Ziyan Luo
  • Qiyue Yin

Natural language generation (NLG) is an important task with various applications like neural machine translation (NMT) and image captioning. Since deep-learning-based methods have issues of exposure bias and loss inconsistency, reinforcement learning (RL) is widely adopted in NLG tasks recently. But most RL-based methods ignore the deviation ignorance issue, which means the model fails to understand the extent of token-level deviation well. It leads to semantic incorrectness and hampers the agent to perform well. To address the issue, we propose a technique called adaptive prior-dependent correction (APDC) to enhance RL. It leverages the distribution generated by computing the distances between the ground truth and all other words to correct the agent’s stochastic policy. Additionally, some techniques on RL are explored to coordinate RL with APDC, which requires a reward estimation at every time step. We find that the RL-based NLG tasks are a special case in RL, where the state transition is deterministic and the afterstate value equals the Q-value at every time step. To utilize such prior knowledge, we estimate the advantage function with the difference of the Q-values which can be estimated by Monte Carlo rollouts. Experiments show that, on three tasks of NLG (NMT, image captioning, abstractive text summarization), our method consistently outperforms the state-of-the-art RL-based approaches on different frequentlyused metrics.

PDF Details

AAAI Conference 2021 Conference Paper

Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series

  • Yinjun Wu
  • Jingchao Ni
  • Wei Cheng
  • Bo Zong
  • Dongjin Song
  • Zhengzhang Chen
  • Yanchi Liu
  • Xuchao Zhang

Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications. However, most existing methods process MTS’s individually, and do not leverage the dynamic distributions underlying the MTS’s, leading to sub-optimal results when the sparsity is high. To address this challenge, we propose a novel generative model, which tracks the transition of latent clusters, instead of isolated feature representations, to achieve robust modeling. It is characterized by a newly designed dynamic Gaussian mixture distribution, which captures the dynamics of clustering structures, and is used for emitting time series. The generative model is parameterized by neural networks. A structured inference network is also designed for enabling inductive analysis. A gating mechanism is further introduced to dynamically tune the Gaussian mixture distributions. Extensive experimental results on a variety of reallife datasets demonstrate the effectiveness of our method.

PDF Details

NeurIPS Conference 2021 Conference Paper

InfoGCL: Information-Aware Graph Contrastive Learning

  • Dongkuan Xu
  • Wei Cheng
  • Dongsheng Luo
  • Haifeng Chen
  • Xiang Zhang

Various graph contrastive learning models have been proposed to improve the performance of tasks on graph datasets in recent years. While effective and prevalent, these models are usually carefully customized. In particular, despite all recent work create two contrastive views, they differ in a variety of view augmentations, architectures, and objectives. It remains an open question how to build your graph contrastive learning model from scratch for particular graph tasks and datasets. In this work, we aim to fill this gap by studying how graph information is transformed and transferred during the contrastive learning process, and proposing an information-aware graph contrastive learning framework called InfoGCL. The key to the success of the proposed framework is to follow the Information Bottleneck principle to reduce the mutual information between contrastive parts while keeping task-relevant information intact at both the levels of the individual module and the entire framework so that the information loss during graph representation learning can be minimized. We show for the first time that all recent graph contrastive learning methods can be unified by our framework. Based on theoretical and empirical analysis on benchmark graph datasets, we show that InfoGCL achieves state-of-the-art performance in the settings of both graph classification and node classification tasks.

PDF Details

AAAI Conference 2021 Conference Paper

Multi-Task Recurrent Modular Networks

  • Dongkuan Xu
  • Wei Cheng
  • Xin Dong
  • Bo Zong
  • Wenchao Yu
  • Jingchao Ni
  • Dongjin Song
  • Xuchao Zhang

We consider the models of deep multi-task learning with recurrent architectures that exploit regularities across tasks to improve the performance of multiple sequence processing tasks jointly. Most existing architectures are painstakingly customized to learn task relationships for different problems, which is not flexible enough to model the dynamic task relationships and lacks generalization abilities to novel test-time scenarios. We propose multi-task recurrent modular networks (MT-RMN) that can be incorporated in any multi-task recurrent models to address the above drawbacks. MT-RMN consists of a shared encoder and multiple task-specific decoders, and recurrently operates over time. For better flexibility, it modularizes the encoder into multiple layers of sub-networks and dynamically controls the connection between these subnetworks and the decoders at different time steps, which provides the recurrent networks with varying degrees of parameter sharing for tasks with dynamic relatedness. For the generalization ability, MT-RMN aims to discover a set of generalizable sub-networks in the encoder that are assembled in different ways for different tasks. The policy networks augmented with the differentiable routers are utilized to make the binary connection decisions between the sub-networks. The experimental results on three multi-task sequence processing datasets consistently demonstrate the effectiveness of MT-RMN.

PDF Details

AAAI Conference 2021 Conference Paper

Transformer-Style Relational Reasoning with Dynamic Memory Updating for Temporal Network Modeling

  • Dongkuan Xu
  • Junjie Liang
  • Wei Cheng
  • Hua Wei
  • Haifeng Chen
  • Xiang Zhang

Network modeling aims to learn the latent representations of nodes such that the representations preserve both network structures and node attribute information. This problem is fundamental due to its prevalence in numerous domains. However, existing approaches either target the static networks or struggle to capture the complicated temporal dependency, while most real-world networks evolve over time and the success of network modeling hinges on the understanding of how entities are temporally connected. In this paper, we present TRRN, a transformer-style relational reasoning network with dynamic memory updating, to deal with the above challenges. TRRN employs multi-head self-attention to reason over a set of memories, which provides a multitude of shortcut paths for information to flow from past observations to the current latent representations. By utilizing the policy networks augmented with differentiable binary routers, TRRN estimates the possibility of each memory being activated and dynamically updates the memories at the time steps when they are most relevant. We evaluate TRRN with the tasks of node classification and link prediction on four real temporal network datasets. Experimental results demonstrate the consistent performance gains for TRRN over the leading competitors.

PDF Details

AAAI Conference 2020 Conference Paper

Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation

  • Xin Dong
  • Jingchao Ni
  • Wei Cheng
  • Zhengzhang Chen
  • Bo Zong
  • Dongjin Song
  • Yanchi Liu
  • Haifeng Chen

Recently, recommender systems have been able to emit substantially improved recommendations by leveraging userprovided reviews. Existing methods typically merge all reviews of a given user (item) into a long document, and then process user and item documents in the same manner. In practice, however, these two sets of reviews are notably different: users’ reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item’s reviews pertain only to that single item and are thus topically homogeneous. In this work, we develop a novel neural network model that properly accounts for this important difference by means of asymmetric attentive modules. The user module learns to attend to only those signals that are relevant with respect to the target item, whereas the item module learns to extract the most salient contents with regard to properties of the item. Our multi-hierarchical paradigm accounts for the fact that neither are all reviews equally useful, nor are all sentences within each review equally pertinent. Extensive experimental results on a variety of real datasets demonstrate the effectiveness of our method.

PDF Details

AAAI Conference 2020 Conference Paper

Deep Unsupervised Binary Coding Networks for Multivariate Time Series Retrieval

  • Dixian Zhu
  • Dongjin Song
  • Yuncong Chen
  • Cristian Lumezanu
  • Wei Cheng
  • Bo Zong
  • Jingchao Ni
  • Takehiko Mizoguchi

Multivariate time series data are becoming increasingly ubiquitous in varies real-world applications such as smart city, power plant monitoring, wearable devices, etc. Given the current time series segment, how to retrieve similar segments within the historical data in an efficient and effective manner is becoming increasingly important. As it can facilitate underlying applications such as system status identification, anomaly detection, etc. Despite the fact that various binary coding techniques can be applied to this task, few of them are specially designed for multivariate time series data in an unsupervised setting. To this end, we present Deep Unsupervised Binary Coding Networks (DUBCNs) to perform multivariate time series retrieval. DUBCNs employ the Long Short-Term Memory (LSTM) encoder-decoder framework to capture the temporal dynamics within the input segment and consist of three key components, i. e. , a temporal encoding mechanism to capture the temporal order of different segments within a mini-batch, a clustering loss on the hidden feature space to capture the hidden feature structure, and an adversarial loss based upon Generative Adversarial Networks (GANs) to enhance the generalization capability of the generated binary codes. Thoroughly empirical studies on three public datasets demonstrated that the proposed DUBCNs can outperform state-of-the-art unsupervised binary coding techniques.

PDF Details

NeurIPS Conference 2020 Conference Paper

Parameterized Explainer for Graph Neural Network

  • Dongsheng Luo
  • Wei Cheng
  • Dongkuan Xu
  • Wenchao Yu
  • Bo Zong
  • Haifeng Chen
  • Xiang Zhang

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method mainly addresses the local explanations (i. e. , important subgraph structure and node features) to interpret why a GNN model makes the prediction for a single instance, e. g. a node or a graph. As a result, the explanation generated is painstakingly customized for each instance. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, as it is designed for explaining a single instance, it is challenging to explain a set of instances naturally (e. g. , graphs of a given class). In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which enables PGExplainer a natural approach to multi-instance explanations. Compared to the existing work, PGExplainer has a better generalization power and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24. 7\% relative improvement in AUC on explaining graph classification over the leading baseline.

PDF Details

AAAI Conference 2020 Conference Paper

Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series

  • Dongkuan Xu
  • Wei Cheng
  • Bo Zong
  • Dongjin Song
  • Jingchao Ni
  • Wenchao Yu
  • Yanchi Liu
  • Haifeng Chen

The problem of learning and forecasting underlying trends in time series data arises in a variety of applications, such as traffic management, energy optimization, etc. In literature, a trend in time series is characterized by the slope and duration, and its prediction is then to forecast the two values of the subsequent trend given historical data of the time series. For this problem, existing approaches mainly deal with the case in univariate time series. However, in many real-world applications, there are multiple variables at play, and handling all of them at the same time is crucial for an accurate prediction. A natural way is to employ multi-task learning (MTL) techniques in which the trend learning of each time series is treated as a task. The key point of MTL is to learn task relatedness to achieve better parameter sharing, which however is challenging in trend prediction task. First, effectively modeling the complex temporal patterns in different tasks is hard as the temporal and spatial dimensions are entangled. Second, the relatedness among tasks may change over time. In this paper, we propose a neural network, DeepTrends, for multivariate time series trend prediction. The core module of Deep- Trends is a tensorized LSTM with adaptive shared memory (TLASM). TLASM employs the tensorized LSTM to model the temporal patterns of long-term trend sequences in an MTL setting. With an adaptive shared memory, TLASM is able to learn the relatedness among tasks adaptively, based upon which it can dynamically vary degrees of parameter sharing among tasks. To further consider short-term patterns, Deep- Trends utilizes a multi-task 1dCNN to learn the local time series features, and employs a task-specific sub-network to learn a mixture of long-term and short-term patterns for trend prediction. Extensive experiments on real datasets demonstrate the effectiveness of the proposed model.

PDF Details

AAAI Conference 2019 Conference Paper

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data

  • Chuxu Zhang
  • Dongjin Song
  • Yuncong Chen
  • Xinyang Feng
  • Cristian Lumezanu
  • Wei Cheng
  • Jingchao Ni
  • Bo Zong

Nowadays, multivariate time series data are increasingly collected in various real world systems, e. g. , power plants, wearable devices, etc. Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in certain time steps and pinpointing the root causes. Building such a system, however, is challenging since it not only requires to capture the temporal dependency in each time series, but also need encode the inter-correlations between different pairs of time series. In addition, the system should be robust to noise and provide operators with different levels of anomaly scores based upon the severity of different incidents. Despite the fact that a number of unsupervised anomaly detection algorithms have been developed, few of them can jointly address these challenges. In this paper, we propose a Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED), to perform anomaly detection and diagnosis in multivariate time series data. Specifically, MSCRED first constructs multi-scale (resolution) signature matrices to characterize multiple levels of the system statuses in different time steps. Subsequently, given the signature matrices, a convolutional encoder is employed to encode the inter-sensor (time series) correlations and an attention based Convolutional Long-Short Term Memory (ConvLSTM) network is developed to capture the temporal patterns. Finally, based upon the feature maps which encode the inter-sensor correlations and temporal information, a convolutional decoder is used to reconstruct the input signature matrices and the residual signature matrices are further utilized to detect and diagnose anomalies. Extensive empirical studies based on a synthetic dataset and a real power plant dataset demonstrate that MSCRED can outperform state-ofthe-art baseline methods.

PDF Details

IJCAI Conference 2019 Conference Paper

Spatio-Temporal Attentive RNN for Node Classification in Temporal Attributed Graphs

  • Dongkuan Xu
  • Wei Cheng
  • Dongsheng Luo
  • Xiao Liu
  • Xiang Zhang

Node classification in graph-structured data aims to classify the nodes where labels are only available for a subset of nodes. This problem has attracted considerable research efforts in recent years. In real-world applications, both graph topology and node attributes evolve over time. Existing techniques, however, mainly focus on static graphs and lack the capability to simultaneously learn both temporal and spatial/structural features. Node classification in temporal attributed graphs is challenging for two major aspects. First, effectively modeling the spatio-temporal contextual information is hard. Second, as temporal and spatial dimensions are entangled, to learn the feature representation of one target node, it’s desirable and challenging to differentiate the relative importance of different factors, such as different neighbors and time periods. In this paper, we propose STAR, a spatio-temporal attentive recurrent network model, to deal with the above challenges. STAR extracts the vector representation of neighborhood by sampling and aggregating local neighbor nodes. It further feeds both the neighborhood representation and node attributes into a gated recurrent unit network to jointly learn the spatio-temporal contextual information. On top of that, we take advantage of the dual attention mechanism to perform a thorough analysis on the model interpretability. Extensive experiments on real datasets demonstrate the effectiveness of the STAR model.

PDF Details

IJCAI Conference 2018 Conference Paper

De-biasing Covariance-Regularized Discriminant Analysis

  • Haoyi Xiong
  • Wei Cheng
  • Yanjie Fu
  • Wenqing Hu
  • Jiang Bian
  • Zhishan Guo

Fisher's Linear Discriminant Analysis (FLD) is a well-known technique for linear classification, feature extraction and dimension reduction. The empirical FLD relies on two key estimations from the data -- the mean vector for each class and the (inverse) covariance matrix. To improve the accuracy of FLD under the High Dimension Low Sample Size (HDLSS) settings, Covariance-Regularized FLD (CRLD) has been proposed to use shrunken covariance estimators, such as Graphical Lasso, to strike a balance between biases and variances. Though CRLD could obtain better classification accuracy, it usually incurs bias and converges to the optimal result with a slower asymptotic rate. Inspired by the recent progress in de-biased Lasso, we propose a novel FLD classifier, DBLD, which improves classification accuracy of CRLD through de-biasing. Theoretical analysis shows that DBLD possesses better asymptotic properties than CRLD. We conduct experiments on both synthetic datasets and real application datasets to confirm the correctness of our theoretical analysis and demonstrate the superiority of DBLD over classical FLD, CRLD and other downstream competitors under HDLSS settings.

PDF Details

IJCAI Conference 2017 Conference Paper

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

  • Yao Qin
  • Dongjin Song
  • Haifeng Chen
  • Wei Cheng
  • Guofei Jiang
  • Garrison W. Cottrell

The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades. Despite the fact that various NARX models have been developed, few of them can capture the long-term temporal dependencies appropriately and select the relevant driving series to make predictions. In this paper, we propose a dual-stage attention-based recurrent neural network (DA-RNN) to address these two issues. In the first stage, we introduce an input attention mechanism to adaptively extract relevant driving series (a. k. a. , input features) at each time step by referring to the previous encoder hidden state. In the second stage, we use a temporal attention mechanism to select relevant encoder hidden states across all time steps. With this dual-stage attention scheme, our model can not only make predictions effectively, but can also be easily interpreted. Thorough empirical studies based upon the SML 2010 dataset and the NASDAQ 100 Stock dataset demonstrate that the DA-RNN can outperform state-of-the-art methods for time series prediction.

PDF Details

IJCAI Conference 2017 Conference Paper

Link Prediction with Spatial and Temporal Consistency in Dynamic Networks

  • Wenchao Yu
  • Wei Cheng
  • Charu C Aggarwal
  • Haifeng Chen
  • Wei Wang

Dynamic networks are ubiquitous. Link prediction in dynamic networks has attracted tremendous research interests. Many models have been developed to predict links that may emerge in the immediate future from the past evolution of the networks. There are two key factors: 1) a node is more likely to form a link in the near future with another node within its close proximity, rather than with a random node; 2) a dynamic network usually evolves smoothly. Existing approaches seldom unify these two factors to strive for the spatial and temporal consistency in a dynamic network. To address this limitation, in this paper, we propose a link prediction model with spatial and temporal consistency (LIST), to predict links in a sequence of networks over time. LIST characterizes the network dynamics as a function of time, which integrates the spatial topology of network at each timestamp and the temporal network evolution. Comparing to existing approaches, LIST has two advantages: 1) LIST uses a generic model to express the network structure as a function of time, which makes it also suitable for a wide variety of temporal network analysis problems beyond the focus of this paper; 2) by retaining the spatial and temporal consistency, LIST yields better prediction performance. Extensive experiments on four real datasets demonstrate the effectiveness of the LIST model.

PDF Details