Author name cluster

Rui Chen

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

33 papers

2 author rows

EAAI Journal 2026 Journal Article

A social recommendation model based on cross-view contrastive learning and multi-head attention for multi-rating fusion

Rui Chen
Zhuo Dai
Wei Lu
Yanbu Guo
Weizhi Meng
Pu Li
Min Huang
Xiangjie Kong

In recent years, social recommender systems have become a hot research field. Contrastive learning effectively enhances the expressiveness of user representations by modeling the consistency of representations between interactive views and social views, thereby improving recommendation performance. This paper proposes a social recommendation model based on cross-view contrastive learning, which employs a multi-head attention mechanism to fuse multi-rating information. It adaptively assigns weights to multiple views, making more effective use of rich social relationships and social trust information to alleviate data sparsity. In the rating view, interaction-aware noise with orientation-preserving constraints is introduced for data augmentation. The proposed model constructs a cross-view contrastive learning task between the rating view and the social view. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed approach and its key components, and reveal that our model consistently outperforms state-of-the-art methods.

Details DOI

FM Conference 2026 Conference Paper

Automated LTL Specification Generation from Industrial Aerospace Requirements

Zhi Ma
Xiao Liang
Cheng Wen
Rui Chen
Bin Gu
Shengchao Qin
Cong Tian
Mengfei Yang

Abstract In the development and verification of safety-critical aero-space software, Linear Temporal Logic (LTL) has been widely used to specify complex system properties derived from requirements. However, a significant gap remains in industrial practice: translating natural language (NL) requirements into formal LTL properties is a labor-intensive and error-prone process that requires rare expertise in both aerospace control engineering and formal methods. While recent NL-to-LTL tools ( e. g. , NL2SPEC, NL2TL, NL2LTL) are capable of automating parts of this process, they often fail on real requirement documents in industrial settings, due to complex domain terminology or implicit temporal and logical structure. To address these challenges, we present Aero Req2LTL, a framework that automates LTL property generation for aerospace requirements using large language models (LLMs), with two key industrial innovations: (i) a data dictionary that normalizes technical jargon into precise atomic propositions; and (ii) a template-based requirement language that makes temporal cues and logical relations explicit before translation. On a real aerospace dataset, Aero Req2LTL achieves 85% precision and 88% recall in LTL generation, and its outputs can be directly consumed by existing verification tools.

DOI

AAMAS Conference 2026 Conference Paper

CoMoU: A Trust-region Model-based Method for Efficient Offline-to-online Reinforcement Learning

Dongxiang Chen
Ying Wen
Rui Chen
Kechen Li

Applying dynamics model is a promising approach to further enhancethesampleefficiencyofoffline-to-onlinereinforcementlearning (O2O RL). The current obstacle is that distribution shift can cause drastic and erroneous updates to dynamics model, just as it has a negative impact on policy. We propose to apply trust-region constraint to the online fine-tuning of offline-trained dynamics model. We prove the avoidance of performance crashes and the unbiasedness of model updates. Experiments verify the enhanced sample efficiency and the optimal asymptotic performance.

PDF

TIST Journal 2026 Journal Article

Matryoshka Representation Learning for Recommendation with Layer- and Hardness-Adaptive Negative Sampling

Riwei Lai
Li Chen
Weixin Chen
Rui Chen

Representation learning is essential for deep-neural-network-based recommender systems to capture user preferences and item features within fixed-dimensional user and item vectors. Unlike existing representation learning methods that either treat each user preference and item feature uniformly or categorize them into discrete clusters, we argue that in the real world, user preferences and item features are naturally expressed and organized in a hierarchical manner, leading to a new direction for representation learning. In this article, we introduce a novel matryoshka representation learning method for recommendation (MRL4Rec), by which we restructure user and item vectors into matryoshka representations with nested vector spaces to explicitly represent user preferences and item features at different hierarchical layers. We theoretically establish that training with the same triplets for each sliced vector cannot guarantee representation learning with hierarchical structures. Subsequently, we propose the layer- and hardness-adaptive negative sampling (LHANS) mechanism to construct training triplets, which further ensures the soundness of learned matryoshka representations in capturing hierarchical user preferences and item features. The experiments demonstrate that MRL4Rec can consistently and substantially outperform a number of state-of-the-art competitors on several real-life datasets. Our code is publicly available at https://github.com/Riwei-HEU/MRL.

Details DOI

EAAI Journal 2025 Journal Article

A hyperparameter-fusion neural networks for deposition prediction

Li Ding
Kun Pang
Junjie Li
Hua Shao
Nan Liu
Rui Chen
Zhiqiang Li
Zhenjie Yao

As integrated circuit manufacturing processes develop into the nanometer scale, precise control and prediction of the deposition process have become crucial. Nanoscale manufacturing imposes unprecedentedly high demands on film quality, uniformity, and consistency, presenting significant challenges to traditional control and prediction methodologies. This study proposes a novel approach that, for the first time, formulates the thin-film deposition process as a video prediction task, enabling the use of deep learning for morphological forecasting under varying process conditions, and introduces a novel hyperparameter-fusion neural network, referred to as DepositionNet (DepoNet). Unlike conventional video prediction models, DepoNet specifically accounts for the influence of deposition parameters on the entire simulation process. We have incorporated a novel Hyper Projector that allows the model to flexibly adapt to varying deposition conditions and material characteristics. Through comprehensive comparative experimental analyses, we demonstrate that DepoNet significantly outperforms existing deep-learning models and achieves a mean squared error of 17. 34, representing a 3. 67% improvement over the second best model and a 1, 435 × speedup over physics-based methods, thereby validating its exceptional generalization capability. Extensive experiments reveal that the model maintains high performance even under conditions of limited training data, for instance, achieving a peak signal-to-noise ratio (PSNR) of 41. 516 decibels (dB) when trained with only 20% of the available data.

Details DOI

EAAI Journal 2025 Journal Article

Etching process prediction based on cascade recurrent neural network

Zhenjie Yao
Ziyi Hu
Panpan Lai
Fengling Qin
Wenrui Wang
Zhicheng Wu
Lingfei Wang
Hua Shao

Etching is one of the most critical processes in semiconductor manufacturing. Etch models have been developed to reveal the underlying etch mechanisms, which employs rigorous physical and chemical process simulation. Traditional simulation is very time consuming. The data-driven artificial intelligence model provides an alternative modeling approach. In this paper, a Cascade Recurrent Neural Networks (CRNN) is proposed to model and predict etching profiles. The etching profile is represented by polar coordinates and modeled by the recurrent neural networks, the corresponding etching parameters (e. g. , pressure, power, temperature, and voltage) are integrated into the network through cascade combination layers. Experimental results on a dataset of 10, 000 simulated etching profiles demonstrated the effectiveness of our method: compared with traditional etching simulation methods, CRNN can speedup 21, 000 × with an average error of less than 0. 7 nm for 1 step prediction. Furthermore, compared to simple deep neural networks, the Mean Absolute Errors (MAE) could be reduced from 1. 7329 nm to 1. 3845 nm for 10 steps prediction. Finally, the effectiveness and accuracy of CRNN etching predictor is validated through fine-tuning on experimental data.

Details DOI

IJCAI Conference 2025 Conference Paper

Exploring Efficient and Effective Sequence Learning for Visual Object Tracking

Dongdong Li
Zhinan Gao
Yangliu Kuai
Rui Chen

Sequence learning based tracking frameworks are popular in the tracking community. In practice, its auto-regressive sequence generation manner leads to inferior performance and high latency compared with latest advanced trackers. In this paper, to mitigate this issue, we propose an efficient and effective sequence-to-sequence tracking framework named FastSeqTrack. FastSeqTrack differs from previous sequence learning based trackers in terms of token initialization and sequence generation manner. Four tracking tokens are appended to patch embeddings and generated in the encoder as initial guesses for the bounding box sequence, which improves the tracking accuracy compared with randomly initialized tokens. Tracking tokens are then parallelly fed into the decoder in a one-pass manner and greatly boost the forward inference speed compared with the auto-regressive manner. Inspired by the early-exit mechanism, we inject internal classifiers after each decoder layer to early terminate forward inference when the softmax confidence is sufficiently reliable. In easy tracking frames, early exits avoid network overthinking and unnecessary computation. Extensive experiments on multiple benchmarks demonstrate that FastSeqTrack runs over 100 fps and showcases superior performance against state-of-the-art trackers. Codes and models are available at https: //github. com/vision4drones/FastSeqTrack.

PDF Details DOI

AAAI Conference 2025 Conference Paper

From Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking

Yuhan Zhao
Rui Chen
Li Chen
Shuang Zhang
Qilong Han
Hongtao Song

Intuitively, an ideal collaborative filtering (CF) model should learn from users' full rankings over all items to make optimal top-K recommendations. Due to the absence of such full rankings in practice, most CF models rely on pairwise loss functions to approximate full rankings, resulting in an immense performance gap. In this paper, we provide a novel analysis using the multiple ordinal classification concept to reveal the inevitable gap between a pairwise approximation and the ideal case. However, bridging the gap in practice encounters two formidable challenges: (1) none of the real-world datasets contains full ranking information; (2) there does not exist a loss function that is capable of consuming ranking information. To overcome these challenges, we propose a pseudo-ranking paradigm (PRP) that addresses the lack of ranking information by introducing pseudo-rankings supervised by an original noise injection mechanism. Additionally, we put forward a new ranking loss function designed to handle ranking information effectively. To ensure our method's robustness against potential inaccuracies in pseudo-rankings, we equip the ranking loss function with a gradient-based confidence mechanism to detect and mitigate abnormal gradients. Extensive experiments on four real-world datasets demonstrate that PRP significantly outperforms state-of-the-art methods.

PDF Details DOI

JBHI Journal 2025 Journal Article

Geometric Deep Learning for Protein-Ligand Affinity Prediction with Hybrid Message Passing Strategies

Jiaren Li
Huasen Jiang
Wenjian Ma
Xiangpeng Bi
Rui Chen
Weigang Lu
Qing Cai
Fei Yang

Accurate prediction of protein-ligand affinity (PLA) is critical for drug discovery. Recent deep learning approaches have adopted data-driven models for PLA prediction by learning intrinsic patterns from one-dimensional (1D) sequential or two-dimensional (2D) graph representations of proteins and ligands. However, these low-dimensional methods overlook the three-dimensional (3D) geometric features, which are hypothesized to be critical in binding interaction. To address the above problem, we present a Geo metric deep learning approach with Hybrid message passing strategies- HybridGeo, for protein-ligand affinity prediction. We adopt dual-view graph learning to model the intra- and inter-molecular atomic interactions and propose to aggregate the spatial information with hybrid strategies. In addition, to fully model the inter-residue dependency upon message aggregation, we adopt a geometric graph transformer on the residue-scale graph of protein pockets. Extensive experiments on the PDBbind dataset show that HybridGeo achieves state-of-the-art performance with a Root Mean Square Error (RMSE) of 1. 172. HybridGeo also achieves the best among all baseline models on three external test sets, showcasing good generalizability and robustness. Through systematic ablation experiments, we validated the effectiveness of the proposed modules, and further demonstrated the superior performance of HybridGeo in predicting the binding affinity of macrocyclic compound complexes through case studies. Visualization analysis further indicates the biological interpretability of the model predictions. Our code is publicly available at https://github.com/anxiangbiye1231/HybridGeo

Details DOI

AIIM Journal 2025 Journal Article

Histopathology image classification based on semantic correlation clustering domain adaptation

Pin Wang
Jinhua Zhang
Yongming Li
Yurou Guo
Pufei Li
Rui Chen

Deep learning has been successfully applied to histopathology image classification tasks. However, the performance of deep models is data-driven, and the acquisition and annotation of pathological image samples are difficult, which limit the model's performance. Compared to whole slide images (WSI) of patients, histopathology image datasets of animal models are easier to acquire and annotate. Therefore, this paper proposes an unsupervised domain adaptation method based on semantic correlation clustering for histopathology image classification. The aim is to utilize Minmice model histopathology image dataset to achieve the classification and recognition of human WSIs. Firstly, the multi-scale fused features extracted from the source and target domains are normalized and mapped. In the new feature space, the cosine distance between class centers is used to measure the semantic correlation between categories. Then, the domain centers, class centers, and sample distributions are self-constrainedly aligned. Multi-granular information is applied to achieve cross-domain semantic correlation knowledge transfer between classes. Finally, the probabilistic heatmap is used to visualize the model's prediction results and annotate the cancerous regions in WSIs. Experimental results show that the proposed method has high classification accuracy for WSI, and the annotated result is close to manual annotation, indicating its potential for clinical applications.

Details DOI

NeurIPS Conference 2025 Conference Paper

Inexact Column Generation for Bayesian Network Structure Learning via Difference-of-Submodular Optimization

Yiran Yang
Rui Chen

In this paper, we consider a score-based Integer Programming (IP) approach for solving the Bayesian Network Structure Learning (BNSL) problem. State-of-the-art BNSL IP formulations suffer from the exponentially large number of variables and constraints. A standard approach in IP to address such challenges is to employ row and column generation techniques, which dynamically generate rows and columns, while the complex pricing problem remains a computational bottleneck for BNSL. For the general class of $\ell_0$-penalized likelihood scores, we show how the pricing problem can be reformulated as a difference of submodular optimization problem, and how the Difference of Convex Algorithm (DCA) can be applied as an inexact method to efficiently solve the pricing problems. Empirically, we show that, for continuous Gaussian data, our row and column generation approach yields solutions with higher quality than state-of-the-art score-based approaches, especially when the graph density increases, and achieves comparable performance against benchmark constraint-based and hybrid approaches, even when the graph size increases.

PDF Details

NeurIPS Conference 2025 Conference Paper

Neighborhood Self-Dissimilarity Attention for Medical Image Segmentation

Junren Chen
Rui Chen
Wei Wang
Junlong Cheng
Gang Liang
Liangyin Chen

Medical image segmentation based on neural networks is pivotal in promoting digital health equity. The attention mechanism increasingly serves as a key component in modern neural networks, as it enables the network to focus on regions of interest, thus improving the segmentation accuracy in medical images. However, current attention mechanisms confront an accuracy-complexity trade-off paradox: accuracy gains demand higher computational costs, while reducing complexity sacrifices model accuracy. Such a contradiction inherently restricts the real-world deployment of attention mechanisms in resource-limited settings, thus exacerbating healthcare disparities. To overcome this dilemma, we propose a parameter-free Neighborhood Self-Dissimilarity Attention (NSDA), inspired by radiologists' diagnostic patterns of prioritizing regions exhibiting substantial differences during clinical image interpretation. Unlike pairwise-similarity-based self-attention mechanisms, NSDA constructs a size-adaptive local dissimilarity measure that quantifies element-neighborhood differences. By assigning higher attention weights to regions with larger feature differences, NSDA directs the neural network to focus on high-discrepancy regions, thus improving segmentation accuracy without adding trainable parameters directly related to computational complexity. The experimental results demonstrate the effectiveness and generalization of our method. This study presents a parameter-free attention paradigm, designed with clinical prior knowledge, to improve neural network performance for medical image analysis and contribute to digital health equity in low-resource settings. The code is available at https: //github. com/ChenJunren-Lab/Neighborhood-Self-Dissimilarity-Attention.

PDF Details

AAAI Conference 2024 Conference Paper

Adaptive Hardness Negative Sampling for Collaborative Filtering

Riwei Lai
Rui Chen
Qilong Han
Chi Zhang
Li Chen

Negative sampling is essential for implicit collaborative filtering to provide proper negative training signals so as to achieve desirable performance. We experimentally unveil a common limitation of all existing negative sampling methods that they can only select negative samples of a fixed hardness level, leading to the false positive problem (FPP) and false negative problem (FNP). We then propose a new paradigm called adaptive hardness negative sampling (AHNS) and discuss its three key criteria. By adaptively selecting negative samples with appropriate hardnesses during the training process, AHNS can well mitigate the impacts of FPP and FNP. Next, we present a concrete instantiation of AHNS called AHNS_{p<0}, and theoretically demonstrate that AHNS_{p<0} can fit the three criteria of AHNS well and achieve a larger lower bound of normalized discounted cumulative gain. Besides, we note that existing negative sampling methods can be regarded as more relaxed cases of AHNS. Finally, we conduct comprehensive experiments, and the results show that AHNS_{p<0} can consistently and substantially outperform several state-of-the-art competitors on multiple datasets.

PDF Details DOI

TMLR Journal 2024 Journal Article

GUARD: A Safe Reinforcement Learning Benchmark

Weiye Zhao
Yifan Sun
Feihan Li
Rui Chen
Ruixuan Liu
Tianhao Wei
Changliu Liu

Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable. Recently, safe RL (i.e. constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints. Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art on-policy safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.

PDF Details

ICLR Conference 2024 Conference Paper

Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice

Jicong Fan 0001
Rui Chen
Zhao Zhang 0001
Chris H. Q. Ding

Neural networks have shown promising performance in collaborative filtering and matrix completion but the theoretical analysis is limited and there is still room for improvement in terms of the accuracy of recovering missing values. This paper presents a neuron-enhanced autoencoder matrix completion (AEMC-NE) method and applies it to collaborative filtering. Our AEMC-NE adds an element-wise autoencoder to each output of the main autoencoder to enhance the reconstruction capability. Thus it can adaptively learn an activation function for the output layer to approximate possibly complicated response functions in real data. We provide theoretical analysis for AEMC-NE as well as AEMC to investigate the generalization ability of autoencoder and deep learning in matrix completion, considering both missing completely at random and missing not at random. We show that the element-wise neural network has the potential to reduce the generalization error bound, the data sparsity can be useful, and the prediction performance is closely related to the difference between the numbers of variables and samples. The numerical results on synthetic data and benchmark datasets demonstrated the effectiveness of AEMC-NE in comparison to many baselines.

Details

TMLR Journal 2024 Journal Article

State-wise Constrained Policy Optimization

Weiye Zhao
Rui Chen
Yifan Sun
Feihan Li
Tianhao Wei
Changliu Liu

Reinforcement Learning (RL) algorithms have shown tremendous success in simulation environments, but their application to real-world problems faces significant challenges, with safety being a major concern. In particular, enforcing state-wise constraints is essential for many challenging tasks such as autonomous driving and robot manipulation. However, existing safe RL algorithms under the framework of Constrained Markov Decision Process (CMDP) do not consider state-wise constraints. To address this gap, we propose State-wise Constrained Policy Optimization (SCPO), the first general-purpose policy search algorithm for state-wise constrained reinforcement learning. SCPO provides guarantees for state-wise constraint satisfaction in expectation. In particular, we introduce the framework of Maximum Markov Decision Process, and prove that the worst-case safety violation is bounded under SCPO. We demonstrate the effectiveness of our approach on training neural network policies for extensive robot locomotion tasks, where the agent must satisfy a variety of state-wise safety constraints. Our results show that SCPO significantly outperforms existing methods and can handle state-wise constraints in high-dimensional robotics tasks.

PDF Details

ICLR Conference 2024 Conference Paper

SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D

Weiyu Li
Rui Chen
Xuelin Chen
Ping Tan

It is inherently ambiguous to lift 2D results from pre-trained diffusion models to a 3D world for text-to-3D generation. 2D diffusion models solely learn view-agnostic priors and thus lack 3D knowledge during the lifting, leading to the multi-view inconsistency problem. We find that this problem primarily stems from geometric inconsistency, and avoiding misplaced geometric structures substantially mitigates the problem in the final outputs. Therefore, we improve the consistency by aligning the 2D geometric priors in diffusion models with well-defined 3D shapes during the lifting, addressing the vast majority of the problem. This is achieved by fine-tuning the 2D diffusion model to be viewpoint-aware and to produce view-specific coordinate maps of canonically oriented 3D objects. In our process, only coarse 3D information is used for aligning. This “coarse” alignment not only resolves the multi-view inconsistency in geometries but also retains the ability in 2D diffusion models to generate detailed and diversified high-quality ob-jects unseen in the 3D datasets. Furthermore, our aligned geometric priors (AGP) are generic and can be seamlessly integrated into various state-of-the-art pipelines, obtaining high generalizability in terms of unseen shapes and visual appearance while greatly alleviating the multi-view inconsistency problem.

Details

NeurIPS Conference 2023 Conference Paper

Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

Zhimeng (Stephen) Jiang
Xiaotian Han
Hongye Jin
Guanchu Wang
Rui Chen
Na Zou
Xia Hu

Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. Subsequently, we analyze the sufficient conditions to guarantee fairness (i. e. , low demographic parity) for the target dataset, including fairness for the source dataset, and low prediction difference between the source and target datasets for each sensitive attribute group. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR) by considering the worst case within the model weight perturbation ball for each sensitive attribute group. We evaluate the effectiveness of our proposed RFR algorithm on synthetic and real distribution shifts across various datasets. Experimental results demonstrate that RFR achieves better fairness-accuracy trade-off performance compared with several baselines. The source code is available at \url{https: //github. com/zhimengj0326/RFR_NeurIPS23}.

PDF Details

TMLR Journal 2023 Journal Article

DSpar: An Embarrassingly Simple Strategy for Efficient GNN training and inference via Degree-based Sparsification

Zirui Liu
Kaixiong Zhou
Zhimeng Jiang
Li Li
Rui Chen
Soo-Hyun Choi
Xia Hu

Running Graph Neural Networks (GNNs) on large graphs suffers from notoriously inefficiency. This is attributed to the sparse graph-based operations, which is hard to be accelerated by community hardware, e.g., GPUs and CPUs. One potential solution is to ``sketch'' the original graph by removing unimportant edges, then both the training and inference process are executed on the sparsified graph with improved efficiency. Traditional graph sparsification work calculates the edge importance score, i.e., effective resistance, from graph topology with theoretical guarantee. However, estimating effective resistance is even more expensive than training GNNs itself. Later, learning-based sparsification methods propose to learn the edge importance from data, but with significant overhead due to the extra learning process. Thus, both of them introduce significant ahead-of-training overhead. In this paper, we experimentally and theoretically prove that effective resistance can be approximated using only the node degree information and achieve similar node presentations on graph with/without sparsification. Based on this finding, we propose DSpar, to sparsify the graph once before training based on only the node degree information with negligible ahead-of-training overhead. In practice, for the training phase, DSpar achieves up to $5.9\times$ faster than baseline with almost no accuracy drop. For the inference phase, DSpar reduces up to $90\%$ latency.

PDF Details

NeurIPS Conference 2023 Conference Paper

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Ruixiang (Ryan) Tang
Jiayi Yuan
Yiming Li
Zirui Liu
Rui Chen
Xia Hu

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the adversaries can embed malicious prediction behaviors by manipulating a few training samples. In this study, our objective is to develop a backdoor-resistant tuning procedure that yields a backdoor-free model, no matter whether the fine-tuning dataset contains poisoned samples. To this end, we propose and integrate an \emph{honeypot module} into the original PLM, specifically designed to absorb backdoor information exclusively. Our design is motivated by the observation that lower-layer representations in PLMs carry sufficient backdoor features while carrying minimal information about the original tasks. Consequently, we can impose penalties on the information acquired by the honeypot module to inhibit backdoor creation during the fine-tuning process of the stem network. Comprehensive experiments conducted on benchmark datasets substantiate the effectiveness and robustness of our defensive strategy. Notably, these results indicate a substantial reduction in the attack success rate ranging from 10\% to 40\% when compared to prior state-of-the-art methods.

PDF Details

IJCAI Conference 2023 Conference Paper

State-wise Safe Reinforcement Learning: A Survey

Weiye Zhao
Tairan He
Rui Chen
Tianhao Wei
Changliu Liu

Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction. State-wise constraints are one of the most common constraints in real-world applications and one of the most challenging constraints in Safe RL. Enforcing state-wise constraints is necessary and essential to many challenging tasks such as autonomous driving, robot manipulation. This paper provides a comprehensive review of existing approaches that address state-wise constraints in RL. Under the framework of State-wise Constrained Markov Decision Process (SCMDP), we will discuss the connections, differences, and trade-offs of existing approaches in terms of (i) safety guarantee and scalability, (ii) safety and reward performance, and (iii) safety after convergence and during training. We also summarize limitations of current methods and discuss potential future directions.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Table2Graph: Transforming Tabular Data to Unified Weighted Graph

Kaixiong Zhou
Zirui Liu
Rui Chen
Li Li
Soo-Hyun Choi
Xia Hu

Learning useful interactions between input features is crucial for tabular data modeling. Recent efforts start to explicitly model the feature interactions with graph, where each feature is treated as an individual node. However, the existing graph construction methods either heuristically formulate a fixed feature-interaction graph based on specific domain knowledge, or simply apply attention function to compute the pairwise feature similarities for each sample. While the fixed graph may be sub-optimal to downstream tasks, the sample-wise graph construction is time-consuming during model training and inference. To tackle these issues, we propose a framework named Table2Graph to transform the feature interaction modeling to learning a unified graph. Represented as a probability adjacency matrix, the unified graph learns to model the key feature interactions shared by the diverse samples in the tabular data. To well optimize the unified graph, we employ the reinforcement learning policy to capture the key feature interactions stably. A sparsity constraint is also proposed to regularize the learned graph from being overly-sparse/smooth. The experimental results in a variety of real-world applications demonstrate the effectiveness and efficiency of our Table2Graph, in terms of the prediction accuracy and feature interaction detection.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition

Yongwei Chen
Rui Chen
Jiabao Lei
Yabin ZHANG
Kui Jia

Creation of 3D content by stylization is a promising yet challenging problem in computer vision and graphics research. In this work, we focus on stylizing photorealistic appearance renderings of a given surface mesh of arbitrary topology. Motivated by the recent surge of cross-modal supervision of the Contrastive Language-Image Pre-training (CLIP) model, we propose TANGO, which transfers the appearance style of a given 3D shape according to a text prompt in a photorealistic manner. Technically, we propose to disentangle the appearance style as the spatially varying bidirectional reflectance distribution function, the local geometric variation, and the lighting condition, which are jointly optimized, via supervision of the CLIP loss, by a spherical Gaussians based differentiable renderer. As such, TANGO enables photorealistic 3D style transfer by automatically predicting reflectance effects even for bare, low-quality meshes, without training on a task-specific dataset. Extensive experiments show that TANGO outperforms existing methods of text-driven 3D style transfer in terms of photorealistic quality, consistency of 3D geometry, and robustness when stylizing low-quality meshes. Our codes and results are available at our project webpage https: //cyw-3d. github. io/tango/.

PDF Details

NeurIPS Conference 2021 Conference Paper

Dirichlet Energy Constrained Learning for Deep Graph Neural Networks

Kaixiong Zhou
Xiao Huang
Daochen Zha
Rui Chen
Li Li
Soo-Hyun Choi
Xia Hu

Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the over-smoothing issue. Node embeddings tend to converge to similar vectors when GNNs keep recursively aggregating the representations of neighbors. To enable deep GNNs, several methods have been explored recently. But they are developed from either techniques in convolutional neural networks or heuristic strategies. There is no generalizable and theoretical principle to guide the design of deep GNNs. To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs. Based on it, a novel deep GNN framework -- Energetic Graph Neural Networks (EGNN) is designed. It could provide lower and upper constraints in terms of Dirichlet energy at each layer to avoid over-smoothing. Experimental results demonstrate that EGNN achieves state-of-the-art performance by using deep layers.

PDF Details

IJCAI Conference 2021 Conference Paper

Fine-Grained Air Quality Inference via Multi-Channel Attention Model

Qilong Han
Dan Lu
Rui Chen

In this paper, we study the problem of fine-grained air quality inference that predicts the air quality level of any location from air quality readings of nearby monitoring stations. We point out the importance of explicitly modeling both static and dynamic spatial correlations, and consequently propose a novel multi-channel attention model (MCAM) that models static and dynamic spatial correlations as separate channels. The static channel combines the beauty of attention mechanisms and graph-based spatial modeling via an adapted bilateral filtering technique, which considers not only locations' Euclidean distances but also their similarity of geo-context features. The dynamic channel learns stations' time-dependent spatial influence on a target location at each time step via long short-term memory (LSTM) networks and attention mechanisms. In addition, we introduce two novel ideas, atmospheric dispersion theories and the hysteretic nature of air pollutant dispersion, to better model the dynamic spatial correlation. We also devise a multi-channel graph convolutional fusion network to effectively fuse the graph outputs, along with other features, from both channels. Our extensive experiments on real-world benchmark datasets demonstrate that MCAM significantly outperforms the state-of-the-art solutions.

PDF Details DOI

ICML Conference 2021 Conference Paper

Integer Programming for Causal Structure Learning in the Presence of Latent Variables

Rui Chen
Sanjeeb Dash
Tian Gao

The problem of finding an ancestral acyclic directed mixed graph (ADMG) that represents the causal relationships between a set of variables is an important area of research on causal inference. Most existing score-based structure learning methods focus on learning directed acyclic graph (DAG) models without latent variables. A number of score-based methods have recently been proposed for the ADMG learning, yet they are heuristic in nature and do not guarantee an optimal solution. We propose a novel exact score-based method that solves an integer programming (IP) formulation and returns a score-maximizing ancestral ADMG for a set of continuous variables that follow a multivariate Gaussian distribution. We generalize the state-of-the-art IP model for DAG learning problems and derive new classes of valid inequalities to formulate an IP model for ADMG learning. Empirically, our model can be solved efficiently for medium-sized problems and achieves better accuracy than state-of-the-art score-based methods as well as benchmark constraint-based methods.

Details

NeurIPS Conference 2020 Conference Paper

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Kaixiong Zhou
Xiao Huang
Yuening Li
Daochen Zha
Rui Chen
Xia Hu

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. It is because the stacked aggregators would make node representations converge to indistinguishable vectors. Several attempts have been made to tackle the issue by bringing linked node pairs close and unlinked pairs distinct. However, they often ignore the intrinsic community structures and would result in sub-optimal performance. The representations of nodes within the same community/class need be similar to facilitate the classification, while different classes are expected to be separated in embedding space. To bridge the gap, we introduce two over-smoothing metrics and a novel technique, i. e. , differentiable group normalization (DGN). It normalizes nodes within the same group independently to increase their smoothness, and separates node distributions among different groups to significantly alleviate the over-smoothing issue. Experiments on real-world datasets demonstrate that DGN makes GNN models more robust to over-smoothing and achieves better performance with deeper GNNs.

PDF Details

IROS Conference 2019 Conference Paper

GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments

Xiaotong Chen
Rui Chen
Zhiqiang Sui
Zhefan Ye
Yanqi Liu
R. Iris Bahar
Odest Chadwicke Jenkins

Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations of these systems. For robot perception, convolutional neural networks (CNNs) for object detection and pose estimation are recently coming into widespread use. However, neural networks are known to suffer from overfitting during the training process and are less robust under unforeseen conditions (which makes them especially vulnerable to adversarial scenarios). In this work, we propose Generative Robust Inference and Perception (GRIP) as a two-stage object detection and pose estimation system that aims to combine the relative strengths of discriminative CNNs and generative inference methods to achieve robust estimation. Our results show that a second stage of sample-based generative inference is able to recover from false object detections by CNNs, and produce robust estimations in adversarial conditions. We demonstrate the efficacy of GRIP robustness through comparison with state-of-the-art learning-based pose estimators and pick-and-place manipulation in dark and cluttered environments.

Details

YNICL Journal 2018 Journal Article

Disrupted brain network topology in chronic insomnia disorder: A resting-state fMRI study

Zhonglin Li
Rui Chen
Min Guan
Enfeng Wang
Tianyi Qian
Cuihua Zhao
Zhi Zou
Thomas Beck

This study investigated the topological characteristics of brain functional networks in chronic insomnia disorder (CID) patients. The resting-state functional magnetic resonance imaging and graph theory analysis method were applied to investigate the brain functional connectome patterns among 45 CID patients and 32 healthy controls. The brain functional connectome was constructed by thresholding partial correlation matrices of 90 brain regions from an automated anatomical labeling atlas. The topologic properties of brain functional connectomes at both global and nodal levels were tested. The CID patients had decreased number of module (p =. 014) and hierarchy (p =. 038), and increased assortativity (p =. 035). Furthermore, some brain regions located in the default mode network, dorsal attention network, and sensory-motor network in these patients showed altered nodal centralities. Within these areas, the node betweenness of right central paracentral lobule had positive correlation with the Pittsburgh Sleep Quality Index score (R = 0. 319, p =. 039). The results imply that functional disruptions of CID patients may be related to disruptions in global and regional topological organization of the brain functional connectome, and provide new and important insights to understand the pathophysiological mechanisms of CID.

Details DOI

IJCAI Conference 2016 Conference Paper

Browsing Regularities in Hedonic Content Systems

Ping Luo
Ganbin Zhou
Jiaxi Tang
Rui Chen
Zhongjie Yu
Qing He

Various hedonic content systems (e. g. mobile apps for video, music, news, jokes, pictures, social networks etc. ) increasingly dominate people's daily spare life. This paper studies common regularities of browsing behaviors in these systems, based on a large data set of user logs. We found that despite differences in visit time and user types, the distribution over browsing length for a visit can be described by the inverse Gaussian form with a very high precision. It indicates that the choice threshold model of decision making on continuing browsing or leave does exist. Also, We found that the stimulus intensity, in terms of the amount of recent enjoyed items, affects the probability of continuing browsing in a curve of inverted-U shape. We discuss the possible origin of this curve based on a proposed Award-Aversion Contest model. This hypothesis is supported by the empirical study, which shows that the proposed model can successfully recover the original inverse Gaussian distribution for the browsing length. These browsing regularities can be used to develop better organization of hedonic content, which helps to attract more user dwell time in these systems.

PDF Details

IROS Conference 2013 Conference Paper

Modeling and analysis of electric field and electrostatic adhesion force generated by interdigital electrodes for wall climbing robots

Rui Chen
Rong Liu
Hua Shen

A model is presented for the analysis of the electric field and electrostatic adhesion force produced by interdigital electrodes. Assuming that the potential varies linearly with distance in inter-electrode gaps, the potential distribution on the electrode plane is obtained by taking the first-order Taylor series approximation. The expressions of electric field components are then derived by solving the Laplace equation for the electrical potential in each subregion. The electrostatic adhesion force is calculated using the Maxwell stress tensor formulation. The dynamic properties of the electric field and electrostatic adhesion force are assessed by evaluating the transient response of the field and force under a step in applied voltages. To verify the model developed, an experimental study is carried out in conjunction with the theoretical analysis to evaluate the adhesion performance of an electrode panel on a glass pane. A double tracked wall climbing robot is designed and tested on various wall surfaces. The limit of the approximation method of the inter-electrode potential is discussed. It is found that vacuum suction force is involved in the adhesion. The influence of this vacuum suction force on electrostatic adhesion is also discussed. The results of this work would provide support for theoretical guidelines and system optimization for the electrostatic adhesion technology applied to wall climbing robots.

Details

IS Journal 2007 Journal Article

Energy and Transportation: A Case Study in China

Rui Chen
Jian Wang

The Chinese government has made a national priority of developing a sustainable, resource- and energy-efficient society. Because the transportation sector is a major energy consumer with significant opportunities for efficiency improvements, it can play a critical role in achieving this national priority. Here, we summarize current energy consumption patterns and describe one study to improve our understanding of the interactions and dependencies among available resources. We analyzed petroleum, coal, and electricity-based energy consumption data in China's transportation sector from 1990 to 2004.

Details DOI

TIME Conference 2001 Conference Paper

Approximate Query Evaluation Using Linear Constraint Databases

Peter Z. Revesz
Rui Chen
Min Ouyang

This paper shows that constraint databases can be used for the approximation of several types of discretely recorded continuous data, for example time series data and some spatio-temporal geographic data. We show that time series data can be approximated by a piecewise linear approximation that runs in linear time in the number of data points, and the piecewise linear approximation can be represented in a linear constraint database. Similarly, the spatio-temporal geographic data that is composed of a set of spatial locations, where each location is associated with a time series, can be also approximated and represented in a linear constraint database. The approximations provide data compression, faster query evaluation-that preserve high precision and recall-and interpolation enabling the evaluation of queries that could not be evaluated before.

Details