Cheng Yang

EAAI Journal 2026 Journal Article

A lightweight residual-driven spatiotemporal prediction model for the global critical frequency of the ionospheric E layer

• Chengsong Duan
• Jian Wang
• Cheng Yang

Accurate prediction of the critical frequency of the ionospheric E layer (foE) is of great significance for radio communication and space weather forecasting. To better capture the spatiotemporal dynamic characteristics of foE and improve the prediction accuracy in short- and medium-term applications, this study proposes a lightweight residual-driven spatiotemporal prediction model that integrates the International Telecommunication Union (ITU) model with observations. The proposed model has the following features: (1) it integrates global, multi-source, heterogeneous ionospheric observations to support model training; (2) it adopts a residual modeling strategy to learn the systematic deviations between observations and ITU predictions; (3) it introduces a Long Short-Term Memory-Multilayer Perceptron (LSTM-MLP) network, which retains the temporal modeling capability of LSTM while leveraging MLP to enhance nonlinear feature learning, thereby enabling synchronous prediction across global stations. Results show that the proposed model outperforms the ITU and LSTM models by 33. 60% and 22. 43%, respectively, achieving superior prediction accuracy, adaptability, and stable generalization across both temporal and spatial evaluations. Moreover, the model completes a global prediction in only 30. 73 s, achieving a 98. 20% efficiency gain over the traditional single-station modeling strategy, while maintaining a parameter scale of just over one million. This high accuracy, high computational efficiency and lightweight design can offer strong support for the stable operation of global radio systems using low ionosphere.

EAAI Journal 2026 Journal Article

Energy consumption optimization control model for highway electromechanical systems integrating digital twins and reinforcement learning

• Xiaming Zeng
• Cheng Yang
• Jie Xue

Existing models for optimizing energy consumption in highway electromechanical systems, often based on static characteristics and offline scheduling, struggle to cope with time-varying, nonlinear dynamics caused by traffic, environment, and equipment aging, leading to inefficiency and delayed safety regulation. To achieve high-efficiency, real-time coordinated control, this study proposes a novel model integrating Digital Twin (DT) and Reinforcement Learning (RL). A multi-physics coupled DT body is first constructed by integrating the illumination, airflow, heat, and electricity dynamics of key subsystems, and a differentiable agent model is embedded in the RL framework to provide a gradient-propagating simulator. Using Proximal Policy Optimization (PPO) as the RL policy, the model minimizes total energy consumption as a negative reward while enforcing operational safety via a Lyapunov stability constraint within the policy optimization process. Online consistency calibration combined with an Extended Kalman Filter (EKF) ensures dynamic virtual-real alignment, and a dual-time-scale architecture splits control into second-level execution and minute-level strategy optimization. Experimental results under extreme coupled conditions show the model achieves energy savings of 18. 5%, 11. 9%, and 8. 6% compared to Proportional-Integral-Derivative (PID), Model Predictive Control (MPC), and standard PPO models, respectively, with an average safety regulation lag of only 23. 3 s. The study concludes that the proposed method enables coordinated energy optimization and real-time safety control under multi-source disturbances and complex coupling conditions, providing a viable path for the intelligent management of highway electromechanical systems.

YNICL Journal 2026 Journal Article

Functional gradient reorganization and transcriptomic signatures underlying 1 Hz rTMS treatment in first-episode schizophrenia following right orbitofrontal cortex stimulation

• Wenwen Miao
• Xiong Jiao
• Ningning Zeng
• Min Wang
• Kexu Zhang
• Cheng Yang
• Yuanjun Xie
• Ziliang Wang

BACKGROUND: The orbitofrontal cortex (OFC) represents a promising yet underexplored neuromodulation target for negative symptoms in schizophrenia, and the macroscale and microscale mechanisms underlying its therapeutic effects remain unclear. METHODS: In a randomized, double-blind, sham-controlled trial, 84 patients with drug-naïve first-episode schizophrenia received consecutive 20 days of active 1-Hz repetitive transcranial magnetic stimulation (rTMS) over the right OFC (n = 45) or sham (n = 39). Resting-state fMRI gradient mapping was integrated with imaging transcriptomics to characterize multiscale neural reorganization and predict treatment response. RESULTS: Active rTMS was associated with greater improvement in negative symptoms and general psychopathology compared with sham stimulation. Gradient analyses indicated a renormalization of macroscale functional hierarchy, with increased principal gradient scores in transmodal nodes (e.g., right middle occipital gyrus and angular gyri) and decreased scores in salience-related regions (e.g., anterior cingulate cortex). These spatial patterns were coupled to transcriptomic signatures enriched for synaptic plasticity and ion transport, with cell-type enrichment implicating cortical interneurons and oligodendrocytes. In addition, baseline gradient topographies in the right middle occipital gyrus and ventral attention network predicted improvements in negative and general symptoms, respectively. CONCLUSIONS: Low-frequency OFC-rTMS was associated with alleviation of negative symptoms in first-episode schizophrenia, alongside a reconfiguration of cortical functional hierarchy. The observed gradient effects were spatially linked to molecular pathways underlying synaptic plasticity and excitation-inhibition regulation, supporting functional gradients as biomarkers for precision neuromodulation in early-stage schizophrenia.

AAAI Conference 2026 Conference Paper

LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules

• Cheng Yang
• Hui Jin
• Xinlei Yu
• Zhipeng Wang
• Yaoqun Liu
• Fenglei Fan
• Dajiang Lei
• Gangyong Jia

Diagnosing lung cancer typically involves physicians identifying lung nodules in Computed tomography (CT) scans and generating diagnostic reports based on their morphological features and medical expertise. Although advancements have been made in using multimodal large language models for analyzing lung CT scans, challenges remain in accurately describing nodule morphology and incorporating medical expertise. These limitations affect the reliability and effectiveness of these models in clinical settings. Collaborative multi-agent systems offer a promising strategy for achieving a balance between generality and precision in medical applications, yet their potential in pathology has not been thoroughly explored. To bridge these gaps, we introduce LungNoduleAgent, an innovative collaborative multi-agent system specifically designed for analyzing lung CT scans. LungNoduleAgent streamlines the diagnostic process into sequential components, improving precision in describing nodules and grading malignancy through three primary modules. The first module, the Nodule Spotter, coordinates clinical detection models to accurately identify nodules. The second module, the Radiologist, integrates localized image description techniques to produce comprehensive CT reports. Finally, the Doctor Agent System performs malignancy reasoning by using images and CT reports, supported by a pathology knowledge base and a multi-agent system framework. Extensive testing on two private datasets and the public LIDC-IDRI dataset indicates that LungNoduleAgent surpasses mainstream vision-language models, agent systems, and advanced expert models such as GPT-4o, Claude 3.7 Sonnet, LLaMA-3.2 Vision, Qwen2.5-VL, Med-R1, MedGemma, MedAgent-Pro, MedAgents, MDAgent and LLaVA-Med. These results highlight the importance of region-level semantic alignment and multi-agent collaboration in diagnosing nodules. LungNoduleAgent stands out as a promising foundational tool for supporting clinical analyses of lung nodules.

AAAI Conference 2026 Conference Paper

PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths

• Boyu Chen
• Zirui Guo
• Zidan Yang
• Yuluo Chen
• Junze Chen
• Zhenghao Liu
• Chuan Shi
• Cheng Yang

Retrieval-augmented generation (RAG) improves the response quality of large language models (LLMs) by retrieving knowledge from external databases. Typical RAG approaches split the text database into chunks, organizing them in a flat structure for efficient searches. To better capture the inherent dependencies and structured relationships across the text database, researchers propose to organize textual information into an indexing graph, known as graph-based RAG. However, we argue that the limitation of current graph-based RAG methods lies in the redundancy of the retrieved information, rather than its insufficiency. Moreover, previous methods use a flat structure to organize retrieved information within the prompts, leading to suboptimal performance. To overcome these limitations, we propose PathRAG, which retrieves key relational paths from the indexing graph, and converts these paths into textual form for prompting LLMs. Specifically, PathRAG effectively reduces redundant information with flow-based pruning, while guiding LLMs to generate more logical and coherent responses with path-based prompting. Experimental results show that PathRAG consistently outperforms state-of-the-art baselines across six datasets and five evaluation dimensions.

TMLR Journal 2025 Journal Article

A Survey on the Honesty of Large Language Models

• Siheng Li
• Cheng Yang
• Taiqiang Wu
• Chufan Shi
• Yuji Zhang
• Xinyu Zhu
• Zesen Cheng
• Deng Cai

Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of related research. To address these issues, we provide a survey on the honesty of LLMs, covering its clarification, evaluation approaches, and strategies for improvement. Moreover, we offer insights for future research, aiming to inspire further exploration in this important area.

AAAI Conference 2025 Conference Paper

Blend the Separated: Mixture of Synergistic Experts for Data-Scarcity Drug-Target Interaction Prediction

• Xinlong Zhai
• Chunchen Wang
• Ruijia Wang
• Jiazheng Kang
• Shujie Li
• Boyu Chen
• Tengfei Ma
• Zikai Zhou

Drug-target interaction prediction (DTI) is essential in various applications including drug discovery and clinical application. There are two perspectives of input data widely used in DTI prediction: Intrinsic data represents how drugs or targets are constructed, and extrinsic data represents how drugs or targets are related to other biological entities. However, any of the two perspectives of input data can be scarce for some drugs or targets, especially for those unpopular or newly discovered. Furthermore, ground-truth labels for specific interaction types can also be scarce. Therefore, we propose the first method to tackle DTI prediction under input data and/or label scarcity. To make our model functional when only one perspective of input data is available, we design two separate experts to process intrinsic and extrinsic data respectively and fuse them adaptively according to different samples. Furthermore, to make the two perspectives complement each other and remedy label scarcity, two experts synergize with each other in a mutually supervised way to exploit the enormous unlabeled data. Extensive experiments on 3 real-world datasets under different extents of input data scarcity and/or label scarcity demonstrate our model outperforms states of the art significantly and steadily, with a maximum improvement of 53.53%. We also test our model without any data scarcity and it still outperforms current methods.

JBHI Journal 2025 Journal Article

Drug Repositioning via Multi-View Representation Learning With Heterogeneous Graph Neural Network

• Li Peng
• Cheng Yang
• Jiahuai Yang
• Yuan Tu
• Qingchun Yu
• Zejun Li
• Min Chen
• Wei Liang

Exploring simple and efficient computational methods for drug repositioning has emerged as a popular and compelling topic in the realm of comprehensive drug development. The crux of this technology lies in identifying potential drug-disease associations, which can effectively mitigate the burdens caused by the exorbitant costs and lengthy periods of conventional drugs development. However, existing computational drug repositioning methods continue to encounter challenges in accurately predicting associations between drugs and diseases. In this paper, we propose a Multi-view Representation Learning method (MRLHGNN) with Heterogeneous Graph Neural Network for drug repositioning. This method is based on a collection of data from multiple biological entities associated with drugs or diseases. It consists of a view-specific feature aggregation module with meta-paths and auto multi-view fusion encoder. To better utilize local structural and semantic information from specific views in heterogeneous graph, MRLHGNN employs a feature aggregation model with variable-length meta-paths to expand the local receptive field. Additionally, it utilizes a transformer based semantic aggregation module to aggregate semantic features across different view-specific graphs. Finally, potential drug-disease associations are obtained through a multi-view fusion decoder with an attention mechanism. Cross-validation experiments demonstrate the effectiveness and interpretability of the MRLHGNN in comparison to nine state-of-the-art approaches. Case studies further reveal that MRLHGNN can serve as a powerful tool for drug repositioning.

AAAI Conference 2025 Conference Paper

Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models

• Yuanzhao Zhai
• Tingkai Yang
• Kele Xu
• Dawei Feng
• Cheng Yang
• Bo Ding
• Huaimin Wang

Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents still face challenges in tasks that require multiple decision-making steps. Estimating the value of actions in specific tasks is difficult when intermediate actions are neither appropriately rewarded nor penalized. In this paper, we propose leveraging a task-relevant Q-value model to guide action selection. Specifically, we first collect decision-making trajectories annotated with step-level Q values via Monte Carlo Tree Search (MCTS) and construct preference data. We then use another LLM to fit these preferences through step-level Direct Policy Optimization (DPO), which serves as the Q-value model. During inference, at each decision-making step, LLM agents select the action with the highest Q value before interacting with the environment. We apply our method to various open-source and API-based LLM agents, demonstrating that Q-value models significantly improve their performance. Notably, the performance of the agent built with Phi-3-mini-4k-instruct improved by 103% on WebShop and 75% on HotPotQA when enhanced with Q-value models, even surpassing GPT-4o-mini. Additionally, Q-value models offer several advantages, such as generalization to different LLM agents and seamless integration with existing prompting strategies.

AAAI Conference 2025 Conference Paper

Federated Graph Condensation with Information Bottleneck Principles

• Bo Yan
• Sihao He
• Cheng Yang
• Shang Liu
• Yang Cao
• Chuan Shi

Graph condensation (GC), which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has benefited various graph learning tasks. However, existing GC methods rely on centralized data storage, which is unfeasible for real-world decentralized data distribution, and overlook data holders' privacy-preserving requirements. To bridge this gap, we propose and study the novel problem of federated graph condensation (FGC) for graph neural networks (GNNs). Specifically, we first propose a general framework for FGC, where we decouple the typical gradient matching process for GC into client-side gradient calculation and server-side gradient matching, integrating knowledge from multiple clients' subgraphs into one smaller condensed graph. Nevertheless, our empirical studies show that under the federated setting, the condensed graph will consistently leak data membership privacy, i.e., the condensed graph during federated training can be utilized to steal training data under the membership inference attack (MIA). To tackle this issue, we innovatively incorporate information bottleneck principles into the FGC, which only needs to extract partial node features in one local pre-training step and utilize the features during federated training. Theoretical and experimental analyses demonstrate that our framework consistently protects membership privacy during training. Meanwhile, it can achieve comparable and even superior performance against existing centralized GC and federated graph learning (FGL) methods.

NeurIPS Conference 2025 Conference Paper

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty

• Xu Wan
• Chao Yang
• Cheng Yang
• Jie Song
• Mingyang Sun

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in Constrained Markov Decision Process (CMDP) form) is equivalent to solving distributionally robust safe RL problems (in robust CMDP form), effectively reformulating the min-max optimization problem into a tractable CMDP with Choquet-integrated value functions. Empirical analyses on safe-control-gym and safety-gymnasium scenarios demonstrate that Fuz-RL effectively integrates with existing safe RL baselines in a model-free manner, significantly improving both safety and control performance under various types of uncertainties in observation, action, and dynamics.

AAAI Conference 2025 Conference Paper

Harnessing Language Model for Cross-Heterogeneity Graph Knowledge Transfer

• Jinyu Yang
• Ruijia Wang
• Cheng Yang
• Bo Yan
• Qimin Zhou
• Yang Juan
• Chuan Shi

Heterogeneous graphs (HGs) that contain various node and edge types are ubiquitous in real-world scenarios. Considering the common label sparsity problem in HGs, some researchers propose to pretrain on source HGs to extract general knowledge and then fine-tune on a target HG for knowledge transfer. However, existing methods often assume that source and target HGs share a single heterogeneity, meaning that they have the same types of nodes and edges, which contradicts the real-world scenarios requiring cross-heterogeneity transfer. Although a recent study has made some preliminary attempts in cross-heterogeneity learning, its definition of general knowledge heavily rely on human knowledge, which lacks flexibility and further leads to a suboptimal transfer. To address the problem, we propose a novel Language Model-enhanced Cross-Heterogeneity learning model, namely LMCH. Specifically, we first design a metapath-based corpus construction method to unify HG representations as languages. The corpora of source HGs are then used to fine-tune a pretrained Language Model (LM), enabling the LM to autonomously extract general knowledge across different HGs. Furthermore, to fully utilize the extensive unlabeled nodes in a few-labeled target HG, we propose an iterative training pipeline with the help of an extra Graph Neural Network (GNN) predictor, enhanced by LM-GNN contrastive alignment at the end of each iteration. Extensive experiments on four real-world datasets have demonstrated the superior performance of LMCH over state-of-the-art methods.

NeurIPS Conference 2025 Conference Paper

Multi-Agent Collaboration via Evolving Orchestration

• Yufan Dang
• Chen Qian
• Xueheng Luo
• Jingru Fan
• Zihao Xie
• Ruijie Shi
• Weize Chen
• Cheng Yang

Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, most approaches rely on static organizational structures that struggle to adapt as task complexity and agent numbers grow, resulting in coordination overhead and inefficiencies. To this end, we propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states. This orchestrator is trained via reinforcement learning to adaptively sequence and prioritize agents, enabling flexible and evolvable collective reasoning. Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs. Analyses further reveal that the key improvements consistently stem from the emergence of more compact, cyclic reasoning structures under the orchestrator’s evolution. Our code is available at https: //github. com/OpenBMB/ChatDev/tree/puppeteer.

IJCAI Conference 2025 Conference Paper

Optimizing Personalized Federated Learning Through Adaptive Layer-Wise Learning

• Weihang Chen
• Cheng Yang
• Jie Ren
• Zhiqiang Li
• Zheng Wang

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

EAAI Journal 2025 Journal Article

Reading comprehension powered semantic fusion network for identification of N-ary drug combinations

• Hua Zhang
• Peiqian Zhan
• Cheng Yang
• Yongjian Yan
• Zijing Cai
• Guogen Shan
• Bo Jiang
• Bi Chen

The concurrent use of multiple medications to treat one or more diseases is prevalent. Identifying N-ary drug combinations from biomedical texts aids in uncovering significant pharmacological effects triggered by drug-drug interactions. Previous methods for this emerging task have primarily concentrated on representing drug entities using pre-trained language models, overlooking the comprehensive extraction of contextual and task-specific semantic information. To address these limitations, we develop a semantic fusion method grounded in machine reading comprehension (MRC) framework. Our model, termed Reading Comprehension powered semantic Fusion network for Identification of N-ary Drug combinations (RCFIND), first constructs relevant contexts and queries for each individual drug combination. Then, diverse information sources, including task-specific semantics, drug entity representations and contextual details, are fused by using a simplified Capsule network as well as incorporating contrastive learning. We assess RCFIND, achieving F1 scores ranging from 72. 0% to 83. 3% across four types of evaluations. Experimental results demonstrate significant performance enhancements over existing baselines, with at least a 5% F1 score improvement. Ablation studies and further analysis confirm the efficacy of the MRC framework and contrastive learning in accurately identifying N-ary drug combinations.

EAAI Journal 2025 Journal Article

Region-based weighting-and-enhancement network with adaptive class weighting loss for postoperative inguinal hernia prediction

• Jiawei Zhang
• Lisheng Wu
• Qiang Fang
• Weidong Yu
• Zhengyu Hu
• Fengyun Zhang
• Cheng Yang
• Xiaoqing Zhang

Postoperative inguinal hernia (PIH) is a common complication after radical prostatectomy, subsequently leading to multiple potential risks (e. g. , cardiovascular and cerebrovascular accidents) and increased surgical costs due to re-surgical reparation. Magnetic resonance imaging (MRI) examination is a widely used procedure before radical prostatectomy, which can investigate the muscle structures of the abdominal wall (MSAW). Recently, clinical studies have indicated that clinical parameters (e. g. , thickness and width of the external oblique muscle) of MSAW are strongly related to PIH. However, automated MRI-based PIH prediction based on deep neural networks has not been studied previously. Motivated by these observations, we propose a novel region-based weighting-and-enhancement network to predict PIH before radical prostatectomy based on MRI images automatically. Specifically, we employ the well-designed Region Weighting-and-Enhancement module to capture informative context representations through region weighting and regional context enhancement, by fully leveraging the potential of clinical MSAW priori. Additionally, this paper designs an effective adaptive class weighting loss to emphasize or suppress the samples with varying levels of significance to further boost the PIH prediction performance. The extensive experiments on a clinical MRI-PIH dataset and one publicly available MRI dataset manifest the superiority of our proposed methods over state-of-the-art deep neural networks and advanced loss methods.

AAAI Conference 2025 Conference Paper

SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning

• Xu Wan
• Chao Yang
• Cheng Yang
• Jie Song
• Mingyang Sun

Although multi-agent reinforcement learning (MARL) has shown its success across diverse domains, extending its application to large-scale real-world systems still faces significant challenges. Primarily, the high complexity of real-world environments exacerbates the credit assignment problem, substantially reducing training efficiency. Moreover, the variability of agent populations in large-scale scenarios necessitates scalable decision-making mechanisms. To address these challenges, we propose a novel framework: Sequential rollout with Sequential value estimation (SrSv). This framework aims to capture agent interdependence and provide a scalable solution for cooperative MARL. Specifically, SrSv leverages the autoregressive property of the Transformer model to handle varying populations through sequential action rollout. Furthermore, to capture the interdependence of policy distributions and value functions among multiple agents, we introduce an innovative sequential value estimation methodology and integrates the value approximation into an attention-based sequential model. We evaluate SrSv on three benchmarks: Multi-Agent MuJoCo, StarCraft Multi-Agent Challenge, and DubinsCars. Experimental results demonstrate that SrSv significantly outperforms baseline methods in terms of training efficiency without compromising convergence performance. Moreover, when implemented in a large-scale DubinsCar system with 1,024 agents, our framework surpasses existing benchmarks, highlighting the excellent scalability of SrSv.

NeurIPS Conference 2024 Conference Paper

AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents

• Chang Ma
• Junlei Zhang
• Zhihao Zhu
• Cheng Yang
• Yujiu Yang
• Yaohui Jin
• Zhenzhong Lan
• Lingpeng Kong

Evaluating large language models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial challenges. A primary obstacle is the benchmarking of agent performance across diverse scenarios within a unified framework, especially in maintaining partially-observable environments and ensuring multi-round interactions. Moreover, current evaluation frameworks mostly focus on the final success rate, revealing few insights during the process and failing to provide a deep understanding of the model abilities. To address these challenges, we introduce AgentBoard, a pioneering comprehensive benchmark and accompanied open-source evaluation framework tailored to analytical evaluation of LLM agents. AgentBoard offers a fine-grained progress rate metric that captures incremental advancements as well as a comprehensive evaluation toolkit that features easy assessment of agents for multi-faceted analysis through interactive visualization. This not only sheds light on the capabilities and limitations of LLM agents but also propels the interpretability of their performance to the forefront. Ultimately, AgentBoard serves as a significant step towards demystifying agent behaviors and accelerating the development of stronger LLM agents.

NeurIPS Conference 2024 Conference Paper

Autonomous Agents for Collaborative Task under Information Asymmetry

• Wei Liu
• Chenxi Wang
• Yifei Wang
• Zihao Xie
• Rennai Qiu
• Yufan Dang
• Zhuoyun Du
• Weize Chen

Large Language Model Multi-Agent Systems (LLM-MAS) have greatly progressed in solving complex tasks. It communicates among agents within the system to collaboratively solve tasks, under the premise of shared information. However, when agents' collaborations are leveraged to perform multi-person tasks, a new challenge arises due to information asymmetry, since each agent can only access the information of its human user. Previous MAS struggle to complete tasks under this condition. To address this, we propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution, thereby overcoming information asymmetry. iAgents employs a novel agent reasoning mechanism, InfoNav, to navigate agents' communication towards effective information exchange. Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange. Additionally, we introduce InformativeBench, the first benchmark tailored for evaluating LLM agents' task-solving ability under information asymmetry. Experimental results show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70, 000 messages to complete tasks within 3 minutes.

NeurIPS Conference 2024 Conference Paper

Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models

• Xin Li
• Weize Chen
• Qizhi Chu
• Haopeng Li
• Zhaojun Sun
• Ran Li
• Chen Qian
• Yiwei Wei

The need to analyze graphs is ubiquitous across various fields, from social networks to biological research and recommendation systems. Therefore, enabling the ability of large language models (LLMs) to process graphs is an important step toward more advanced general intelligence. However, current LLM benchmarks on graph analysis require models to directly reason over the prompts describing graphtopology, and are thus limited to small graphs with only a few dozens of nodes. In contrast, human experts typically write programs based on popular libraries for task solving, and can thus handle graphs with different scales. To this end, a question naturally arises: can LLMs analyze graphs like professionals? In this paper, we introduce ProGraph, a manually crafted benchmark containing 3 categories of graph tasks. The benchmark expects solutions based on programming instead of directly reasoning over raw inputs. Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy. To bridge this gap, we propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries. By augmenting closed-source LLMs with document retrieval and fine-tuning open-source ones on the codes, we show 11-32% absolute improvements in their accuracies. Our results underscore that the capabilities of LLMs in handling structured data are still under-explored, and show the effectiveness of LLM4Graph in enhancing LLMs’ proficiency of graph analysis. The benchmark, datasets and enhanced open-sourcemodels are available at https: //github. com/BUPT-GAMMA/ProGraph.

AAAI Conference 2024 Conference Paper

FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization

• Cheng Yang
• Jixi Liu
• Yunhe Yan
• Chuan Shi

Despite the remarkable success of graph neural networks (GNNs) in modeling graph-structured data, like other machine learning models, GNNs are also susceptible to making biased predictions based on sensitive attributes, such as race and gender. For fairness consideration, recent state-of-the-art (SOTA) methods propose to filter out sensitive information from inputs or representations, e.g., edge dropping or feature masking. However, we argue that such filtering-based strategies may also filter out some non-sensitive feature information, leading to a sub-optimal trade-off between predictive performance and fairness. To address this issue, we unveil an innovative neutralization-based paradigm, where additional Fairness-facilitating Features (F3) are incorporated into node features or representations before message passing. The F3 are expected to statistically neutralize the sensitive bias in node representations and provide additional nonsensitive information. We also provide theoretical explanations for our rationale, concluding that F3 can be realized by emphasizing the features of each node’s heterogeneous neighbors (neighbors with different sensitive attributes). We name our method as FairSIN, and present three implementation variants from both data-centric and model-centric perspectives. Experimental results on five benchmark datasets with three different GNN backbones show that FairSIN significantly improves fairness metrics while maintaining high prediction accuracies. Codes and appendix can be found at https://github.com/BUPT-GAMMA/FariSIN.

NeurIPS Conference 2024 Conference Paper

GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent

• Hongtai Zeng
• Chao Yang
• Yanzhen Zhou
• Cheng Yang
• Qinglai Guo

Ensuring that the outputs of neural networks satisfy specific constraints is crucial for applying neural networks to real-life decision-making problems. In this paper, we consider making a batch of neural network outputs satisfy bounded and general linear constraints. We first reformulate the neural network output projection problem as an entropy-regularized linear programming problem. We show that such a problem can be equivalently transformed into an unconstrained convex optimization problem with Lipschitz continuous gradient according to the duality theorem. Then, based on an accelerated gradient descent algorithm with numerical performance enhancement, we present our architecture, GLinSAT, to solve the problem. To the best of our knowledge, this is the first general linear satisfiability layer in which all the operations are differentiable and matrix-factorization-free. Despite the fact that we can explicitly perform backpropagation based on automatic differentiation mechanism, we also provide an alternative approach in GLinSAT to calculate the derivatives based on implicit differentiation of the optimality condition. Experimental results on constrained traveling salesman problems, partial graph matching with outliers, predictive portfolio allocation and power system unit commitment demonstrate the advantages of GLinSAT over existing satisfiability layers. Our implementation is available at https: //github. com/HunterTracer/GLinSAT.

AAAI Conference 2024 Conference Paper

Graph Invariant Learning with Subgraph Co-mixup for Out-of-Distribution Generalization

• Tianrui Jia
• Haoyang Li
• Cheng Yang
• Tao Tao
• Chuan Shi

Graph neural networks (GNNs) have been demonstrated to perform well in graph representation learning, but always lacking in generalization capability when tackling out-of-distribution (OOD) data. Graph invariant learning methods, backed by the invariance principle among defined multiple environments, have shown effectiveness in dealing with this issue. However, existing methods heavily rely on well-predefined or accurately generated environment partitions, which are hard to be obtained in practice, leading to sub-optimal OOD generalization performances. In this paper, we propose a novel graph invariant learning method based on invariant and variant patterns co-mixup strategy, which is capable of jointly generating mixed multiple environments and capturing invariant patterns from the mixed graph data. Specifically, we first adopt a subgraph extractor to identify invariant subgraphs. Subsequently, we design one novel co-mixup strategy, i.e., jointly conducting environment mixup and invariant mixup. For the environment mixup, we mix the variant environment-related subgraphs so as to generate sufficiently diverse multiple environments, which is important to guarantee the quality of the graph invariant learning. For the invariant mixup, we mix the invariant subgraphs, further encouraging to capture invariant patterns behind graphs while getting rid of spurious correlations for OOD generalization. We demonstrate that the proposed environment mixup and invariant mixup can mutually promote each other. Extensive experiments on both synthetic and real-world datasets demonstrate that our method significantly outperforms state-of-the-art under various distribution shifts.

IJCAI Conference 2024 Conference Paper

Heterogeneous Graph Transformer with Poly-Tokenization

• Zhiyuan Lu
• Yuan Fang
• Cheng Yang
• Chuan Shi

Graph neural networks have shown widespread success for learning on graphs, but they still face fundamental drawbacks, such as limited expressive power, over-smoothing, and over-squashing. Meanwhile, the transformer architecture offers a potential solution to these issues. However, existing graph transformers primarily cater to homogeneous graphs and are unable to model the intricate semantics of heterogeneous graphs. Moreover, unlike small molecular graphs where the entire graph can be considered as the receptive field in graph transformers, real-world heterogeneous graphs comprise a significantly larger number of nodes and cannot be entirely treated as such. Consequently, existing graph transformers struggle to capture the long-range dependencies in these complex heterogeneous graphs. To address these two limitations, we present Poly-tokenized Heterogeneous Graph Transformer (PHGT), a novel transformer-based heterogeneous graph model. In addition to traditional node tokens, PHGT introduces a novel poly-token design with two more token types: semantic tokens and global tokens. Semantic tokens encapsulate high-order heterogeneous semantic relationships, while global tokens capture semantic-aware long-range interactions. We validate the effectiveness of PHGT through extensive experiments on standardized heterogeneous graph benchmarks, demonstrating significant improvements over state-of-the-art heterogeneous graph representation learning models.

EAAI Journal 2024 Journal Article

Query-induced multi-task decomposition and enhanced learning for aspect-based sentiment quadruple prediction

• Hua Zhang
• Xiawen Song
• Xiaohui Jia
• Cheng Yang
• Zeqi Chen
• Bi Chen
• Bo Jiang
• Ye Wang

A complete sentiment analysis of product and service reviews has attracted growing concerns from merchants to enhance personalized marketing activities. Aspect sentiment quadruple prediction (ASQP) is a demanding and challenging task with the objective to predict four sentiment elements from given reviews. Existing methods for ASQP face certain issues, with pipeline-based non-generative approaches prone to error propagation and generative models at the potential risk of producing unexpected outputs or longer inference times. To avoid these shortcomings, we develop a novel end-to-end non-generative model for ASQP involving multi-task decomposition within machine reading comprehension (MRC) framework. Specifically, the ASQP task is decomposed into six query-induced subtasks by introducing task-specific question templates. The proposed model, named MRC-CLRI, is trained with multi-task joint learning. It also incorporates contrastive learning for category identification and sentiment classification to enhance the correlation of the six subtasks. To further promote the quadruple prediction, we present a refined inference algorithm in a bidirectional multi-turn inference procedure to effectively match aspect and opinion terms and optimize two inference hyperparameters: distance threshold and probability threshold. Experimental results exhibit superior performance compared to existing two non-generative and seven generative baselines. Our proposed MRC-CLRI, as a novel non-generative model, outperforms the best existing generative method by an average F1 score improvement of 1. 69% and the best previous non-generative method by an average F1 score improvement of 15. 77% across four review datasets. Ablation experiments further validate the efficacy of the designed contrastive learning and the refined inference algorithm.

NeurIPS Conference 2024 Conference Paper

Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast

• Chufan Shi
• Cheng Yang
• Xinyu Zhu
• Jiahao Wang
• Taiqiang Wu
• Siheng Li
• Deng Cai
• Yujiu Yang

Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing mechanism. However, the unchosen experts in MoE models do not contribute to the output, potentially leading to underutilization of the model's capacity. In this work, we first conduct exploratory studies to demonstrate that increasing the number of activated experts does not necessarily improve and can even degrade the output quality. Then, we show that output distributions from an MoE model using different routing strategies substantially differ, indicating that different experts do not always act synergistically. Motivated by these findings, we propose S elf- C ontrast M ixture- o f- E xperts (SCMoE), a training-free strategy that utilizes unchosen experts in a self-contrast manner during inference. In SCMoE, the next-token probabilities are determined by contrasting the outputs from strong and weak activation using the same MoE model. Our method is conceptually simple and computationally lightweight, as it incurs minimal latency compared to greedy decoding. Experiments on several benchmarks (GSM8K, StrategyQA, MBPP and HumanEval) demonstrate that SCMoE can consistently enhance Mixtral 8x7B’s reasoning capability across various domains. For example, it improves the accuracy on GSM8K from 61. 79 to 66. 94. Moreover, combining SCMoE with self-consistency yields additional gains, increasing major@20 accuracy from 75. 59 to 78. 31.

TMLR Journal 2024 Journal Article

Vision Learners Meet Web Image-Text Pairs

• Bingchen Zhao
• Quan Cui
• Hao Wu
• Osamu Yoshie
• Cheng Yang
• Oisin Mac Aodha

Most recent self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data. First, we conduct a benchmark study of representative self-supervised pre-training methods on large-scale web data in a like-for-like setting. We compare a range of methods, including single-modal ones that use masked training objectives and multi-modal ones that use image-text constrastive training. We observe that existing multi-modal methods do not outperform their single-modal counterparts on vision transfer learning tasks. We derive an information-theoretical view to explain these benchmark results, which provides insight into how to design a novel vision learner. Inspired by this insight, we present a new visual representation pre-training method, MUlti-modal Generator~(MUG), that learns from scalable web sourced image-text data. MUG achieves state-of-the-art transfer performance on a variety of tasks and demonstrates promising scaling properties. Pre-trained models and code will be made public upon acceptance.

AAMAS Conference 2023 Conference Paper

Efficient Interactive Recommendation via Huffman Tree-based Policy Learning

• Longxiang Shi
• Zilin Zhang
• Shoujin Wang
• Binbin Zhou
• Minghui Wu
• Cheng Yang
• Shijian Li

Interactive recommender systems (IRSs) are an essential part of our daily life, as they can suggest items to persistently satisfy our demands. Due to the interactive nature, conventional static recommendation methods such as matrix factorization, and content-based filtering are ineffective to capture the dynamic preferences of users. Recently, reinforcement learning (RL) has shown great potential in addressing the challenges in IRSs, since it can capture users’ dynamic preferences and model the long-term profit of user-item interactions. However, millions of items in real-world IRSs lead to a large discrete action space in the RL setting, rendering RL-based IRSs inefficient and hindering their widespread application. Such an inefficiency issue has not been well addressed in the literature. In order to address this issue, we propose a novel Huffman Tree Policy Recommendation (HTPR) framework. Specifically, a novel policy learning network based on a newly designed Huffman tree is proposed for policy representation learning, which effectively improves the learning efficiency. Moreover, a novel parameter-sharing scheme is devised to further reduce unnecessary computations. Extensive experiments on two real-world benchmark datasets demonstrate the superiority of HTPR over the state-of-the-art IRS methods in terms of both recommendation accuracy and efficiency.

NeurIPS Conference 2023 Conference Paper

Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization

• Ruijia Wang
• YiWu Sun
• Yujie Luo
• Shaochuan Li
• Cheng Yang
• Xingyi Cheng
• Hui Li
• Chuan Shi

The structure of protein-protein complexes is critical for understanding binding dynamics, biological mechanisms, and intervention strategies. Rigid protein docking, a fundamental problem in this field, aims to predict the 3D structure of complexes from their unbound states without conformational changes. In this scenario, we have access to two types of valuable information: sequence-modal information, such as coevolutionary data obtained from multiple sequence alignments, and structure-modal information, including the 3D conformations of rigid structures. However, existing docking methods typically utilize single-modal information, resulting in suboptimal predictions. In this paper, we propose xTrimoBiDock (or BiDock for short), a novel rigid docking model that effectively integrates sequence- and structure-modal information through bi-level optimization. Specifically, a cross-modal transformer combines multimodal information to predict an inter-protein distance map. To achieve rigid docking, the roto-translation transformation is optimized to align the docked pose with the predicted distance map. In order to tackle this bi-level optimization problem, we unroll the gradient descent of the inner loop and further derive a better initialization for roto-translation transformation based on spectral estimation. Compared to baselines, BiDock achieves a promising result of a maximum 234% relative improvement in challenging antibody-antigen docking problem.

AAAI Conference 2023 Conference Paper

MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning

• Xumeng Gong
• Cheng Yang
• Chuan Shi

Contrastive learning (CL), which can extract the information shared between different contrastive views, has become a popular paradigm for vision representation learning. Inspired by the success in computer vision, recent work introduces CL into graph modeling, dubbed as graph contrastive learning (GCL). However, generating contrastive views in graphs is more challenging than that in images, since we have little prior knowledge on how to significantly augment a graph without changing its labels. We argue that typical data augmentation techniques (e.g., edge dropping) in GCL cannot generate diverse enough contrastive views to filter out noises. Moreover, previous GCL methods employ two view encoders with exactly the same neural architecture and tied parameters, which further harms the diversity of augmented views. To address this limitation, we propose a novel paradigm named model augmented GCL (MA-GCL), which will focus on manipulating the architectures of view encoders instead of perturbing graph inputs. Specifically, we present three easy-to-implement model augmentation tricks for GCL, namely asymmetric, random and shuffling, which can respectively help alleviate high-frequency noises, enrich training instances and bring safer augmentations. All three tricks are compatible with typical data augmentations. Experimental results show that MA-GCL can achieve state-of-the-art performance on node classification benchmarks by applying the three tricks on a simple base model. Extensive studies also validate our motivation and the effectiveness of each trick. (Code, data and appendix are available at https://github.com/GXM1141/MA-GCL. )

JBHI Journal 2023 Journal Article

Predicting CircRNA-Disease Associations via Feature Convolution Learning With Heterogeneous Graph Attention Network

• Li Peng
• Cheng Yang
• Yifan Chen
• Wei Liu

Exploring the relationship between circular RNA (circRNA) and disease is beneficial for revealing the mechanisms of disease pathogenesis. However, a blind search for all possible associations between circRNAs and diseases through biological experiments is time-consuming. Although some prediction methods have been proposed, they still have limitations. In this study, a novel computational framework, called GATCL2CD, is proposed to forecast unknown circRNA-disease associations (CDAs). First, we calculate Gaussian interactive profile kernel (GIP) similarity and semantic similarity for diseases, circRNA sequence similarity and function similarity, and GIPs for circRNAs. Then, we combine them to construct a heterogeneous graph. Thereafter, GATCL2CD proposes a feature convolution learning framework, that uses a multi-head dynamic attention mechanism to obtain different aggregated representations of features that correspond to the nodes in the heterogeneous graph. Then, it extracts rich higher-order features from the stacked feature representations of each node by using of a single-layer convolutional neural network with filter kernels of different sizes. Finally, a pairwise element-wise product operation is implemented to capture the interactions of higher-order feature representations, and a multilayer perceptron neural network is introduced as an efficient classifier for inferring potential CDAs. Major experimental results under 5-fold cross-validation (5-fold CV) on three different datasets show that GATCL2CD is superior to five other state-of-the-art methods. Furthermore, case studies demonstrate the suitability of GATCL2CD as a useful tool for identifying potential disease-related circRNAs.

AAAI Conference 2022 Conference Paper

SAS: Self-Augmentation Strategy for Language Model Pre-training

• Yifei Xu
• Jingqiao Zhang
• Ru He
• Liangzhu Ge
• Chao Yang
• Cheng Yang
• Ying Nian Wu

The core of self-supervised learning for pre-training language models includes pre-training task design as well as appropriate data augmentation. Most data augmentations in language model pre-training are context-independent. A seminal contextualized augmentation was recently proposed in ELECTRA and achieved state-of-the-art performance by introducing an auxiliary generation network (generator) to produce contextualized data augmentation for the training of a main discrimination network (discriminator). This design, however, introduces extra computation cost of the generator and a need to adjust the relative capability between the generator and the discriminator. In this paper, we propose a self-augmentation strategy (SAS) where a single network is utilized for both regular pre-training and contextualized data augmentation for the training in later epochs. Essentially, this strategy eliminates a separate generator and uses the single network to jointly conduct two pre-training tasks with MLM (Masked Language Modeling) and RTD (Replaced Token Detection) heads. It avoids the challenge to search for an appropriate size of the generator, which is critical to the performance as evidenced in ELECTRA and its subsequent variant models. In addition, SAS is a general strategy that can be seamlessly combined with many new techniques emerging recently or in the future, such as the disentangled attention mechanism from DeBERTa. Our experiments show that SAS outperforms ELECTRA and other state-of-the-art models in the GLUE tasks with similar or less computation cost.

AAAI Conference 2022 Conference Paper

TransFG: A Transformer Architecture for Fine-Grained Recognition

• Ju He
• Jie-Neng Chen
• Shuai Liu
• Adam Kortylewski
• Cheng Yang
• Yutong Bai
• Changhu Wang

Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the backbone network to extract features of detected discriminative regions. However, this strategy inevitably complicates the pipeline and pushes the proposed regions to contain most parts of the objects thus fails to locate the really important parts. Recently, vision transformer (ViT) shows its strong performance in the traditional classification task. The selfattention mechanism of the transformer links every patch token to the classification token. In this work, we first evaluate the effectiveness of the ViT framework in the fine-grained recognition setting. Then motivated by the strength of the attention link can be intuitively considered as an indicator of the importance of tokens, we further propose a novel Part Selection Module that can be applied to most of the transformer architectures where we integrate all raw attention weights of the transformer into an attention map for guiding the network to effectively and accurately select discriminative image patches and compute their relations. A contrastive loss is applied to enlarge the distance between feature representations of confusing classes. We name the augmented transformer-based model TransFG and demonstrate the value of it by conducting experiments on five popular fine-grained benchmarks where we achieve state-of-the-art performance. Qualitative results are presented for better understanding of our model.

NeurIPS Conference 2021 Conference Paper

Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration

• Xiao Wang
• Hongrui Liu
• Chuan Shi
• Cheng Yang

Despite Graph Neural Networks (GNNs) have achieved remarkable accuracy, whether the results are trustworthy is still unexplored. Previous studies suggest that many modern neural networks are over-confident on the predictions, however, surprisingly, we discover that GNNs are primarily in the opposite direction, i. e. , GNNs are under-confident. Therefore, the confidence calibration for GNNs is highly desired. In this paper, we propose a novel trustworthy GNN model by designing a topology-aware post-hoc calibration function. Specifically, we first verify that the confidence distribution in a graph has homophily property, and this finding inspires us to design a calibration GNN model (CaGCN) to learn the calibration function. CaGCN is able to obtain a unique transformation from logits of GNNs to the calibrated confidence for each node, meanwhile, such transformation is able to preserve the order between classes, satisfying the accuracy-preserving property. Moreover, we apply the calibration GNN to self-training framework, showing that more trustworthy pseudo labels can be obtained with the calibrated confidence and further improve the performance. Extensive experiments demonstrate the effectiveness of our proposed model in terms of both calibration and accuracy.

ICLR Conference 2021 Conference Paper

Nonseparable Symplectic Neural Networks

• Shiying Xiong
• Yunjin Tong
• Xingzhe He
• Shuqi Yang
• Cheng Yang
• Bo Zhu 0002

Predicting the behaviors of Hamiltonian systems has been drawing increasing attention in scientific machine learning. However, the vast majority of the literature was focused on predicting separable Hamiltonian systems with their kinematic and potential energy terms being explicitly decoupled, while building data-driven paradigms to predict nonseparable Hamiltonian systems that are ubiquitous in fluid dynamics and quantum mechanics were rarely explored. The main computational challenge lies in the effective embedding of symplectic priors to describe the inherently coupled evolution of position and momentum, which typically exhibits intricate dynamics. To solve the problem, we propose a novel neural network architecture, Nonseparable Symplectic Neural Networks (NSSNNs), to uncover and embed the symplectic structure of a nonseparable Hamiltonian system from limited observation data. The enabling mechanics of our approach is an augmented symplectic time integrator to decouple the position and momentum energy terms and facilitate their evolution. We demonstrated the efficacy and versatility of our method by predicting a wide range of Hamiltonian systems, both separable and nonseparable, including chaotic vortical flows. We showed the unique computational merits of our approach to yield long-term, accurate, and robust predictions for large-scale Hamiltonian systems by rigorously enforcing symplectomorphism.

AAAI Conference 2020 Conference Paper

MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space

• Xiaoyuan Yi
• Ruoyu Li
• Cheng Yang
• Wenhao Li
• Maosong Sun

As an essential step towards computer creativity, automatic poetry generation has gained increasing attention these years. Though recent neural models make prominent progress in some criteria of poetry quality, generated poems still suffer from the problem of poor diversity. Related literature researches show that different factors, such as life experience, historical background, etc. , would influence composition styles of poets, which considerably contributes to the high diversity of human-authored poetry. Inspired by this, we propose MixPoet, a novel model that absorbs multiple factors to create various styles and promote diversity. Based on a semi-supervised variational autoencoder, our model disentangles the latent space into some subspaces, with each conditioned on one influence factor by adversarial training. In this way, the model learns a controllable latent variable to capture and mix generalized factor-related properties. Different factor mixtures lead to diverse styles and hence further differentiate generated poems from each other. Experiment results on Chinese poetry demonstrate that MixPoet improves both diversity and quality against three state-of-the-art models.

IJCAI Conference 2020 Conference Paper

PewLSTM: Periodic LSTM with Weather-Aware Gating Mechanism for Parking Behavior Prediction

• Feng Zhang
• Ningxuan Feng
• Yani Liu
• Cheng Yang
• Jidong Zhai
• Shuhao Zhang
• Bingsheng He
• Jiazao Lin

In big cities, there are plenty of parking spaces, but we often find nowhere to park. For example, New York has 1. 4 million cars and 4. 4 million on-street parking spaces, but it is still not easy to find a parking place near our destination, especially during peak hours. The reason is the lack of prediction of parking behavior. If we could provide parking behavior in advance, we can ease this parking problem that affects human well-being. We observe that parking lots have periodic parking patterns, which is an important factor for parking behavior prediction. Unfortunately, existing work ignores such periodic parking patterns in parking behavior prediction, and thus incurs low accuracy. To solve this problem, we propose PewLSTM, a novel periodic weather-aware LSTM model that successfully predicts the parking behavior based on historical records, weather, environments, and weekdays. PewLSTM has been successfully integrated into a real parking space reservation system, ThsParking, which is one of the top smart parking platforms in China. Based on 452, 480real parking records in 683 days from 10 parking lots, PewLSTM yields 85. 3% parking prediction accuracy, which is about 20% higher than the state-of-the-art parking behavior prediction method. The code and data can be obtained fromhttps: //github. com/NingxuanFeng/PewLSTM.

IJCAI Conference 2019 Conference Paper

A Practical Semi-Parametric Contextual Bandit

• Yi Peng
• Miao Xie
• Jiahao Liu
• Xuying Meng
• Nan Li
• Cheng Yang
• Tao Yao
• Rong Jin

Classic multi-armed bandit algorithms are inefficient for a large number of arms. On the other hand, contextual bandit algorithms are more efficient, but they suffer from a large regret due to the bias of reward estimation with finite dimensional features. Although recent studies proposed semi-parametric bandits to overcome these defects, they assume arms' features are constant over time. However, this assumption rarely holds in practice, since real-world problems often involve underlying processes that are dynamically evolving over time especially for the special promotions like Singles' Day sales. In this paper, we formulate a novel Semi-Parametric Contextual Bandit Problem to relax this assumption. For this problem, a novel Two-Steps Upper-Confidence Bound framework, called Semi-Parametric UCB (SPUCB), is presented. It can be flexibly applied to linear parametric function problem with a satisfied gap-free bound on the n-step regret. Moreover, to make our method more practical in online system, an optimization is proposed for dealing with high dimensional features of a linear function. Extensive experiments on synthetic data as well as a real dataset from one of the largest e-commercial platforms demonstrate the superior performance of our algorithm.

IJCAI Conference 2019 Conference Paper

Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks

• Cheng Yang
• Jian Tang
• Maosong Sun
• Ganqu Cui
• Zhiyuan Liu

Information diffusion prediction is an important task which studies how information items spread among users. With the success of deep learning techniques, recurrent neural networks (RNNs) have shown their powerful capability in modeling information diffusion as sequential data. However, previous works focused on either microscopic diffusion prediction which aims at guessing the next influenced user or macroscopic diffusion prediction which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, no previous works have suggested a unified model for both microscopic and macroscopic scales. In this paper, we propose a novel multi-scale diffusion prediction model based on reinforcement learning (RL). RL incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the non-differentiable problem. We also employ an effective structural context extraction strategy to utilize the underlying social graph information. Experimental results show that our proposed model outperforms state-of-the-art baseline models on both microscopic and macroscopic diffusion predictions on three real-world datasets.

AAAI Conference 2019 Conference Paper

Robust Online Matching with User Arrival Distribution Drift

• Yu-Hang Zhou
• Chen Liang
• Nan Li
• Cheng Yang
• Shenghuo Zhu
• Rong Jin

Recently, online matching problems have attracted much attention due to its emerging applications in internet advertising. Most existing online matching methods have adopted either adversarial or stochastic user arrival assumption, while on both of them significant limitation exists. The adversarial model does not exploit existing knowledge of the user sequence, and thus can be pessimistic in practice. On other hands, the stochastic model assumes that users are drawn from a stationary distribution, which may not be true in real applications. In this paper, we consider a novel user arrival model where users are drawn from drifting distribution, which is a hybrid case between the adversarial and stochastic model, and propose a new approach RDLA to deal with such assumption. Instead of maximizing empirical total revenues on the revealed users, RDLA leverages distributionally robust optimization techniques to learn dual variables via a worst-case consideration over an ambiguity set on the underlying user distribution. Experiments on a real-world dataset exhibit the superiority of our approach.

AAAI Conference 2019 Conference Paper

Semi-Parametric Sampling for Stochastic Bandits with Many Arms

• Mingdong Ou
• Nan Li
• Cheng Yang
• Shenghuo Zhu
• Rong Jin

We consider the stochastic bandit problem with a large candidate arm set. In this setting, classic multi-armed bandit algorithms, which assume independence among arms and adopt non-parametric reward model, are inefficient, due to the large number of arms. By exploiting arm correlations based on a parametric reward model with arm features, contextual bandit algorithms are more efficient, but they can also suffer from large regret in practical applications, due to the reward estimation bias from mis-specified model assumption or incomplete features. In this paper, we propose a novel Bayesian framework, called Semi-Parametric Sampling (SPS), for this problem, which employs semi-parametric function as the reward model. Specifically, the parametric part of SPS, which models expected reward as a parametric function of arm feature, can efficiently eliminate poor arms from candidate set. The non-parametric part of SPS, which adopts nonparametric reward model, revises the parametric estimation to avoid estimation bias, especially on the remained candidate arms. We give an implementation of SPS, Linear SPS (LSPS), which utilizes linear function as the parametric part. In semi-parametric environment, theoretical analysis shows that LSPS achieves better regret bound (i. e. Õ( √ N 1−α dα √ T) with α ∈ [0, 1]) than existing approaches. Also, experiments demonstrate the superiority of the proposed approach.

IJCAI Conference 2019 Conference Paper

Sentiment-Controllable Chinese Poetry Generation

• Huimin Chen
• Xiaoyuan Yi
• Maosong Sun
• Wenhao Li
• Cheng Yang
• Zhipeng Guo

Expressing diverse sentiments is one of the main purposes of human poetry creation. Existing Chinese poetry generation models have made great progress in poetry quality, but they all neglected to endow generated poems with specific sentiments. Such defect leads to strong sentiment collapse or bias and thus hurts the diversity and semantics of generated poems. Meanwhile, there are few sentimental Chinese poetry resources for studying. To address this problem, we first collect a manually-labelled sentimental poetry corpus with fine-grained sentiment labels. Then we propose a novel semi-supervised conditional Variational Auto-Encoder model for sentiment-controllable poetry generation. Besides, since poetry is discourse-level text where the polarity and intensity of sentiment could transfer among lines, we incorporate a temporal module to capture sentiment transition patterns among different lines. Experimental results show our model can control the sentiment of not only a whole poem but also each line, and improve the poetry diversity against the state-of-the-art models without losing quality.

AAAI Conference 2018 Conference Paper

Chinese LIWC Lexicon Expansion via Hierarchical Classification of Word Embeddings with Sememe Attention

• Xiangkai Zeng
• Cheng Yang
• Cunchao Tu
• Zhiyuan Liu
• Maosong Sun

Linguistic Inquiry and Word Count (LIWC) is a word counting software tool which has been used for quantitative text analysis in many fields. Due to its success and popularity, the core lexicon has been translated into Chinese and many other languages. However, the lexicon only contains several thousand of words, which is deficient compared with the number of common words in Chinese. Current approaches often require manually expanding the lexicon, but it often takes too much time and requires linguistic experts to extend the lexicon. To address this issue, we propose to expand the LIWC lexicon automatically. Specifically, we consider it as a hierarchical classification problem and utilize the Sequence-to-Sequence model to classify words in the lexicon. Moreover, we use the sememe information with the attention mechanism to capture the exact meanings of a word, so that we can expand a more precise and comprehensive lexicon. The experimental results show that our model has a better understanding of word meanings with the help of sememes and achieves significant and consistent improvements compared with the state-of-the-art methods. The source code of this paper can be obtained from https: //github. com/thunlp/Auto CLIWC.

IJCAI Conference 2017 Conference Paper

Fast Network Embedding Enhancement via High Order Proximity Approximation

• Cheng Yang
• Maosong Sun
• Zhiyuan Liu
• Cunchao Tu

Many Network Representation Learning (NRL) methods have been proposed to learn vector representations for vertices in a network recently. In this paper, we summarize most existing NRL methods into a unified two-step framework, including proximity matrix construction and dimension reduction. We focus on the analysis of proximity matrix construction step and conclude that an NRL method can be improved by exploring higher order proximities when building the proximity matrix. We propose Network Embedding Update (NEU) algorithm which implicitly approximates higher order proximities with theoretical approximation bound and can be applied on any NRL methods to enhance their performances. We conduct experiments on multi-label classification and link prediction tasks. Experimental results show that NEU can make a consistent and significant improvement over a number of NRL methods with almost negligible running time on all three publicly available datasets.

IJCAI Conference 2015 Conference Paper

Network Representation Learning with Rich Text Information

• Cheng Yang
• Zhiyuan Liu
• Deli Zhao
• Maosong Sun
• Edward Chang

Representation learning has shown its effectiveness in many tasks such as image classification and text mining. Network representation learning aims at learning distributed vector representation for each vertex in a network, which is also increasingly recognized as an important aspect for network analysis. Most network representation learning methods investigate network structures for learning. In reality, network vertices contain rich information (such as text), which cannot be well applied with algorithmic frameworks of typical representation learning methods. By proving that DeepWalk, a state-ofthe-art network representation method, is actually equivalent to matrix factorization (MF), we propose text-associated DeepWalk (TADW). TADW incorporates text features of vertices into network representation learning under the framework of matrix factorization. We evaluate our method and various baseline methods by applying them to the task of multi-class classification of vertices. The experimental results show that, our method outperforms other baselines on all three datasets, especially when networks are noisy and training ratio is small. The source code of this paper can be obtained from https: //github. com/albertyang33/TADW.

JMLR Journal 2011 Journal Article

A Refined Margin Analysis for Boosting Algorithms via Equilibrium Margin

• Liwei Wang
• Masashi Sugiyama
• Zhaoxiang Jing
• Cheng Yang
• Zhi-Hua Zhou
• Jufu Feng

Much attention has been paid to the theoretical explanation of the empirical success of AdaBoost. The most influential work is the margin theory, which is essentially an upper bound for the generalization error of any voting classifier in terms of the margin distribution over the training data. However, important questions were raised about the margin explanation. Breiman (1999) proved a bound in terms of the minimum margin, which is sharper than the margin distribution bound. He argued that the minimum margin would be better in predicting the generalization error. Grove and Schuurmans (1998) developed an algorithm called LP-AdaBoost which maximizes the minimum margin while keeping all other factors the same as AdaBoost. In experiments however, LP-AdaBoost usually performs worse than AdaBoost, putting the margin explanation into serious doubt. In this paper, we make a refined analysis of the margin theory. We prove a bound in terms of a new margin measure called the Equilibrium margin (Emargin). The Emargin bound is uniformly sharper than Breiman's minimum margin bound. Thus our result suggests that the minimum margin may be not crucial for the generalization error. We also show that a large Emargin and a small empirical error at Emargin imply a smaller bound of the generalization error. Experimental results on benchmark data sets demonstrate that AdaBoost usually has a larger Emargin and a smaller test error than LP-AdaBoost, which agrees well with our theory. [abs] [ pdf ][ bib ] &copy JMLR 2011. ( edit, beta )

ICML Conference 2007 Conference Paper

On learning with dissimilarity functions

• Liwei Wang 0001
• Cheng Yang
• Jufu Feng