Xing Chen

TMLR Journal 2026 Journal Article

A Tighter Bound for Reward Learning in Reinforcement Learning from Human Feedback

• Guoxi Chen
• Xing Chen
• Bo An
• Ya Zhang

As a key component of reinforcement learning from human feedback (RLHF), reward learning directly influences the final learned policy. Unfortunately, existing theoretical estimation error bounds in reward learning rely on the complexity of the reward function class, unattainable optimal parameters, or non-zero constants independent of sample size, leading to uncomputable bounds that are meaningless for reward function classes with unknown complexity. To address this issue, this paper presents an analysis of parameter estimation for reward learning in RLHF under general function approximation, without imposing restrictions on the complexity of the reward function class. A tighter bound is provided without non-zero terms independent of the sample size. The optimal parameters are eliminated by applying linear approximation around the learned parameters. Additionally, the relationship between the preference dataset and the learned parameters is further examined to demonstrate how to efficiently collect data based on the current learned parameters. Inspired by the theoretical results, a novel offline RLHF algorithm with parameter constraints is proposed, restricting parameters to the valid space defined by the dataset. Furthermore, an online RLHF algorithm is proposed to iteratively optimize parameter learning and improve data collection efficiency. This work provides a tighter bound than previous studies and offers theoretical guidance for online data collection under general function approximation.

AAAI Conference 2026 Conference Paper

Bridging Optimization and Neural Networks for Efficient Multi-view Clustering

• Huilang Xu
• Xiang-Xiang Su
• Simin Chen
• Guang-Yong Chen
• Xing Chen

Multi-view clustering (MVC) seeks to uncover the intrinsic group structures embedded in multi-view data, which has attracted considerable attention in recent years. Existing approaches predominantly concentrate on incorporating suitable model priors to capture consistency across views. However, these explicit constraints often fail to hold in scenarios involving significant modal differences between views or the presence of noise, thereby limiting the efficacy of these methods in more complex contexts. To address these issues, this paper introduces BONE, a lightweight and interpretable MVC framework that Bridges Optimization and Neural networks for Efficient MVC. By leveraging learnable parameters to extract high-level features from low-level features derived through classical optimization, BONE integrates the consistency information across views without the need for explicit prior constraints, while eliminating the necessity for pre-training or post-processing. Extensive experiments show that BONE achieves clustering performance comparable to or even better than existing deep MVC methods, while using only 1% of the parameters, offering a new perspective for designing efficient MVC algorithms.

JBHI Journal 2025 Journal Article

DTI-MvSCA: An Anti-Over-Smoothing Multi-View Framework With Negative Sample Selection for Predicting Drug-Target Interactions

• Lihong Peng
• Zongzheng Bai
• Longlong Liu
• Long Yang
• Xin Liu
• Min Chen
• Xing Chen

Predicting potential drug-target interactions (DTIs) facilitates to accelerate drug discovery and reduce development cost. Current deep learning-based methods exhibit high-performance predictions, but three challenges remain: first, the absence of negative DTIs severely limits the model performance. Moreover, existing graph neural networks are beset with the scalability due to the model complexity and graph size. More importantly, most methods focus on learning the topological features while ignoring node features during DTI representation learning. To solve the limitations, here, we develop a multi-view neural network framework called DTI-MvSCA for DTI identification. This framework begins with constructing a drug-protein pair (DPP) network with matrix operation-based negative DTI selection, and then learns the DPP representations through a M ulti- v iew neural network, finally classifies each DPP based on multilayer perceptron. Particularly, the multi-view neural network integrates graph topological feature learning based on the self-attention mechanism and S HADOW graph attention network, node feature learning based on 1D C onvolutional neural network, and the A ttention mechanism. An in-depth experiment on DrugBank V3. 0 and V5. 0 showed that DTI-MvSCA obtained precise and robust predictions against five state-of-the-art baseline methods. Furthermore, visualizing the feature distributions of the selected negative DTIs exhibits a more distinguishable and clearer boundary. In summary, DTI-MvSCA provides a useful deep learning tool to investigate potential DTIs.

JBHI Journal 2025 Journal Article

Exploring Microbe-Drug Association Prediction via Multi-Attribute Dual-Decoder Graph Autoencoder

• Wei Liu
• Xiangcheng Deng
• Xingen Sun
• Xu Lu
• Xing Chen

Predicting potential microbe-drug associations (MDA) can help study pathogenesis, expedite pharmaceutical innovation, and enhance targeted therapeutics. Given the time and labor intensity of traditional biological experiments, an increasing number of computational approaches are being employed to predict MDA. The method based on graph embedding is one of the most widely used. However, most of these methods only consider node embedding or graph structure information in isolation, which leads to restricted predictive accuracy. In this work, we propose a method called exploring microbe-drug association prediction via multi-attribute dual-decoder graph autoencoder (MDGAEMDA). Specifically, a heterogeneous network containing microbe similarity, drug similarity, and known associations is constructed. Second, to enrich the node information, the multi-attribute features are obtained by importing the topological information of microbe and drug. Then, two heterogeneous networks constructed by the graph masking strategy are input into dual-decoder graph autoencoder that contains one encoder and two decoders (node decoder and structure decoder) to learn both node embedding and graph structure information. Finally, two low-dimensional features are spliced into the features of MDA pairs and predicted by random forest. The model was compared with multiple advanced methods using public datasets. The experimental outcomes showed that our model significantly outperformed other methods. The case study of widely used drugs demonstrated the reliability of the proposed method to predict MDA.

JBHI Journal 2025 Journal Article

Guest Editorial:Application of Computational Techniques in Drug Discovery and Disease Treatment

• Xing Chen
• Qi Zhao

JBHI Journal 2024 Journal Article

CellDialog: A Computational Framework for Ligand-Receptor-Mediated Cell-Cell Communication Analysis

• Lihong Peng
• Wei Xiong
• Chendi Han
• Zejun Li
• Xing Chen

Intercellularcommunication significantly influences tumor progression, metastasis, and therapy resistance. An intercellular communication inference method includes two main procedures: ligand-receptor interaction (LRI) curation and LRI-mediated intercellular communication strength measurement. The construction of a comprehensive, high-confident and well-organized LRI database contributes to intercellular communication inference. Here, we developed a computational framework named CellDialog to reconstruct an intercellular connectivity network based on the combined expression of ligands and receptors involved in sender and receiver cells. CellDialog first captures high-confident LRIs through LRI feature extraction, feature selection, and classification. Furthermore, CellDialog uses a three-point estimation approach to measure the LRI-mediated intercellular communication strength by combining LRI filtering and single-cell RNA sequencing data. A comparison analysis of CellDialog and the other tools was conducted, and it was found that CellDialog can efficiently decode intercellular communications. Additionally, CellDialog offers a heatmap view and network view for intercellular communication visualization. In summary, CellDialog provides a tool that allows researchers to analyze intercellular signal transduction.

AAAI Conference 2024 Conference Paper

EMGAN: Early-Mix-GAN on Extracting Server-Side Model in Split Federated Learning

• Jingtao Li
• Xing Chen
• Li Yang
• Adnan Siraj Rakin
• Deliang Fan
• Chaitali Chakrabarti

Split Federated Learning (SFL) is an emerging edge-friendly version of Federated Learning (FL), where clients process a small portion of the entire model. While SFL was considered to be resistant to Model Extraction Attack (MEA) by design, a recent work shows it is not necessarily the case. In general, gradient-based MEAs are not effective on a target model that is changing, as is the case in training-from-scratch applications. In this work, we propose a strong MEA during the SFL training phase. The proposed Early-Mix-GAN (EMGAN) attack effectively exploits gradient queries regardless of data assumptions. EMGAN adopts three key components to address the problem of inconsistent gradients. Specifically, it employs (i) Early-learner approach for better adaptability, (ii) Multi-GAN approach to introduce randomness in generator training to mitigate mode collapse, and (iii) ProperMix to effectively augment the limited amount of synthetic data for a better approximation of the target domain data distribution. EMGAN achieves excellent results in extracting server-side models. With only 50 training samples, EMGAN successfully extracts a 5-layer server-side model of VGG-11 on CIFAR-10, with 7% less accuracy than the target model. With zero training data, the extracted model achieves 81.3% accuracy, which is significantly better than the 45.5% accuracy of the model extracted by the SoTA method. The code is available at "https://github.com/zlijingtao/SFL-MEA".

EAAI Journal 2023 Journal Article

Ada-CCFNet: Classification of multimodal direct immunofluorescence images for membranous nephropathy via adaptive weighted confidence calibration fusion network

• Ruili Wang
• Xueyu Liu
• Fang Hao
• Xing Chen
• Xinyu Li
• Chen Wang
• Dan Niu
• Ming Li

In the pathological diagnosis of early, late and non-membranous nephropathy, direct immunofluorescence is highly likely to present potentially specific lesions, while it is often overlooked due to the difficulty of screening with naked eyes. With the advanced progress of deep learning, they have shown powerful abilities in detecting potential lesions. In this paper, we propose an adaptive weighted confidence calibration fusion framework (Ada-CCFNet) consisting of a preprocessing module, an adaptive weighted confidence calibration fusion (Ada-CCF) module and a classification module for diagnosis of membranous nephropathy by classifying the multimodal direct immunofluorescence images. In the preprocessing module, we use the well-known U-Net to segment individual glomeruli and standardize their luminance appearance by the average luminance difference method, allowing the subsequent modules to focus more on the diseased glomerular region. Subsequently, in the Ada-CCF module, six confidence calibration methods are utilized for two main direct immunofluorescence images, IgG and C3, and the comprehensive calibration scores are obtained based on the adaptive weighted fusion of six confidence calibration methods to obtain more reliable confidence level, in which the adaptive weights are related with expected calibration error reductions. For the classification module, the weighted probability scores of IgG and C3 are jointly fed into the module to achieve the classification by random forest. Experimental results showed that Ada-CCFNet achieves the classification accuracy of 73. 52%, surpassing the methods of using single IgG or C3 images and positive grade indicator with 8. 24%, 8. 94% and 22. 76%, and outperforming the compared methods in the classification of membranous nephropathy.

AAAI Conference 2023 Conference Paper

The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure

• Xing Chen
• Dongcui Diao
• Hechang Chen
• Hengshuai Yao
• Haiyin Piao
• Zhixiao Sun
• Zhiwei Yang
• Randy Goebel

The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is "YES", and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in "off-policyness", according to an off-policy metric called DEON. Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservative Policy Iteration (CPI) objective better than PPO during training. To the best of our knowledge, all current PPO methods have the clipping operation and optimize in the clipped policy space. Our method is the first of this kind, which advances the understanding of CPI optimization and policy gradient methods. Code is available at https://github.com/raincchio/P3O.

EAAI Journal 2021 Journal Article

Multi-agent hierarchical policy gradient for Air Combat Tactics emergence via self-play

• Zhixiao Sun
• Haiyin Piao
• Zhen Yang
• Yiyang Zhao
• Guang Zhan
• Deyun Zhou
• Guanglei Meng
• Hechang Chen

Air-to-air confrontation has attracted wide attention from artificial intelligence scholars. However, in the complex air combat process, operational strategy selection depends heavily on aviation expert knowledge, which is usually expensive and difficult to obtain. Moreover, it is challenging to select optimal action sequences efficiently and accurately with existing methods, due to the high complexity of action selection when involving hybrid actions, e. g. , discrete/continuous actions. In view of this, we propose a novel Multi-Agent Hierarchical Policy Gradient algorithm (MAHPG), which is capable of learning various strategies and transcending expert cognition by adversarial self-play learning. Besides, a hierarchical decision network is adopted to deal with the complicated and hybrid actions. It has a hierarchical decision-making ability similar to humankind, and thus, reduces the action ambiguity efficiently. Extensive experimental results demonstrate that the MAHPG outperforms the state-of-the-art air combat methods in terms of both defense and offense ability. Notably, it is discovered that the MAHPG has the ability of Air Combat Tactics Interplay Adaptation, and new operational strategies emerged that surpass the level of experts.

AAAI Conference 2012 Conference Paper

Recommending Related Microblogs: A Comparison Between Topic and WordNet based Approaches

• Xing Chen
• Lin Li
• Guandong Xu
• Zhenglu Yang
• Masaru Kitsuregawa

Computing similarity between short microblogs is an important step in microblog recommendation. In this paper, we investigate a topic based approach and a WordNet based approach to estimate similarity scores between microblogs and recommend top related ones to users. Empirical study is conducted to compare their recommendation effectiveness using two evaluation measures. The results show that the WordNet based approach has relatively higher precision than that of the topic based approach using 548 tweets as dataset. In addition, the Kendall tau distance between two lists recommended by WordNet and topic approaches is calculated. Its average of all the 548 pair lists tells us the two approaches have the relative high disaccord in the ranking of related tweets.

ICRA Conference 2003 Conference Paper

Foveated observation of shape and motion

• James Davis 0001
• Xing Chen

Robotic navigation and interaction frequently require that the shape and motion of external objects and events be observed. Many interesting events occur at mixed scales. Subtle localized shape and motion often occurs together with long-range movements. One of the chief challenges in recovering these events is to obtain high resolution imagery suitable for resolving small details, while simultaneously increasing the working volume in which recovery is possible. This paper proposes architecture for mixed scale motion recovery. The robust coverage of a large working volume is provided by a wide area of tracking system. This system localizes interesting motions, and guides a separate foveated system of pan tilt cameras to observe the detailed event at high resolution. We demonstrate two applications, foveated structured light scanning and the capture of muscle deformation while walking. Both applications allow subtle detailed recovery that would not be possible using existing single scale systems.