Author name cluster

Chuan 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.

18 papers

1 author row

AAAI Conference 2026 Conference Paper

FedLAGC: Towards High Performance System-Heterogeneous Federated Learning via Layer-Adaptive Submodel Extraction and Gradient Correction

Qing Hu
Tianchi Liao
Shuyi Wu
Lei Yang
Chuan Chen

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, many existing FL methods implicitly assume that clients have sufficient computational and storage resources, making them less applicable in real-world scenarios with severe system heterogeneity. To address this, submodel extraction has recently gained attention as a promising strategy to tailor the global model to resource-constrained clients. Despite this progress, existing methods often suffer from noticeable performance gaps across clients and structural inconsistency in the extracted models, leading to degraded global performance and increased communication overhead. In this work, we propose FedLAGC, a novel federated framework that jointly tackles performance imbalance and communication inefficiency through Layer-Adaptive submodel extraction and Gradient Correction. Specifically, FedLAGC constructs client-specific submodels by selecting structurally important parameters according to layer-wise importance scores, ensuring both resource adaptiveness and architectural consistency. Additionally, we propose a lightweight correction mechanism that captures historical optimization drift, helping to align local updates with the global direction and reduce redundant communication. The rigorous convergence analysis of FedLAGC for system-heterogeneous federated learning under non-convex objectives is given. Extensive experiments on CIFAR-10 and CIFAR-100 with ResNet-18 and ResNet-34 under various system and data heterogeneity settings demonstrate the significant superiority of FedLAGC (up to 24% accuracy improvement and 3.66× communication efficiency) over state-of-the-art methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Beyond Federated Prototype Learning: Learnable Semantic Anchors with Hyperspherical Contrast for Domain-Skewed Data

Lele Fu
Sheng Huang
Yanyi Lai
Tianchi Liao
Chuanfu Zhang
Chuan Chen

Federated prototype learning is in the spotlight as global prototypes are effective in enhancing the learning of local representation spaces, facilitating the ability to generalize the global model. However, when encountering domain-skewed data, conventional federated prototype learning is susceptible to two dilemmas: 1) Local prototypes obtained by averaging intra-class embedding carry domain-specific markers, the margins among aggregated global prototypes could be attenuated and detrimental to inter-class separation. 2) Local domain-skewed embedding may not exhibit a uniform distribution in Euclidean space, which is not conductive to the prototype-induced intra-class compactness. To address the two drawbacks, we go beyond conventional paradigm of federated prototype learning, and propose learnable semantic anchors with hyperspherical contrast (FedLSA) for domain-skewed data. Specifically, we eschew the pattern of yielding prototypes via averaging intra-class embedding and directly learn a set of semantic anchors aided by the global semantic-aware classifier. Meanwhile, the margins between anchors are augmented via pulling apart them, ensuring decent inter-class separation. To guarantee that local domain-skewed representations can be uniformly distributed, local data is projected into the hyperspherical space, and the intra-class compactness is achieved by optimizing the contrastive loss derived from the von Mises-Fisher distribution. Finally, extensive experimental results on three multi-domain datasets show the superiority of the proposed FedLSA compared to existing typical and state-of-the-state methods.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

FedBG: Proactively Mitigating Bias in Cross-Domain Graph Federated Learning Using Background Data

Sheng Huang
Lele Fu
Tianchi Liao
Bowen Deng
Chuanfu Zhang
Chuan Chen

Federated graph learning is focused on aggregating knowledge from multi-source graph data and training graph neural networks. Unlike the data that traditional federated learning needs to deal with, federated graph learning also needs to face additional topological information. Further, there are also biases in features and topologies among clients, increasing the difficulty of training models. Previous methods usually seek global calibration information, however, this approach may suffer from information bias caused by data skews, and it is also difficult to naturally combine feature and topology information. Therefore, adjusting the bias before it occurs will hopefully address the learning difficulties caused by the skew. In view of this, we employ background graph data, which works as reference information for local training, to proactively correct bias before it occurs. As a kind of graph data, background graphs are naturally capable of combining feature and topology information to accomplish bias correction among clients in a comprehensive way. Mixing strategy is employed on the background graph to additionally provide privacy-preserving capabilities. Graph generation methods are employed to restore the diversity of background graphs that are blurred by the mixing strategy. Extensive experiments on two real-world datasets demonstrate the sufficient motivation and effectiveness of the proposed method.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Federated Domain Generalization with Decision Insight Matrix

Tianchi Liao
Binghui Xie
Lele Fu
Sheng Huang
Bowen Deng
Chuan Chen
Zibin Zheng

Federated domain generalization addresses the crucial challenge of developing models that can generalize across diverse domains while maintaining data privacy in federated learning settings. Current approaches either compromise privacy constraints or focus narrowly on specific aspects of model invariance, often incurring significant computational overhead. We propose a novel approach FedDIM, which leverages the concept of “insight matrix” - a fine-grained representation of the model's decision-making process derived from element-wise products between feature vectors and classifier weights. By introducing a regularization term that promotes consistency between individual sample insight matrices and their class-wise mean representations, our method effectively captures both feature and classifier invariance. This approach not only maintains strict privacy requirements but also introduces minimal computational overhead as it utilizes intermediate computations already present in the forward pass. Extensive experiments demonstrate that our method achieves superior out-of-distribution generalization compared to existing federated learning approaches while being simple to implement. Our work provides a new perspective on achieving robust generalization in federated learning settings through the lens of decision-making processes.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

GLNCD: Graph-Level Novel Category Discovery

Bowen Deng
Lele Fu
Sheng Huang
Tianchi Liao
Jialong Chen
Zhang Tao
Chuan Chen

Graph classification has long assumed a closed-world setting, limiting its applicability to real-world scenarios where new categories often emerge. To address this limitation, we introduce Graph-Level Novel Category Discovery (GLNCD), a new task aimed at identifying unseen graph categories without supervision from novel classes. We first adapt classical Novel Category Discovery (NCD) methods for images to the graph domain and evaluate these baseline methods on four diverse graph datasets curated for the GLNCD task. Our analysis reveals that these methods suffer a notable performance degradation compared to their image-based counterparts, due to two key challenges: (1) insufficient utilization of structural information in graph self-supervised learning (SSL), and (2) ineffective pseudo-labeling strategies based on ranking statistics (RS) that neglect graph structure. To alleviate these issues, we propose ProtoFGW-NCD, a framework consisting of two core components: ProtoFGW-CL, a novel graph SSL framework, and FGW-RS, a structure-aware pseudo-labeling method. Both components employ a differentiable Fused Gromov-Wasserstein (FGW) distance to effectively compare graphs by incorporating structural information. These components are built upon learnable prototype graphs, which enable efficient, parallel FGW-based graph comparisons and capture representative patterns within graph datasets. Experiments on four GLNCD benchmark datasets demonstrate the effectiveness of ProtoFGW-NCD.

PDF Details

IJCAI Conference 2025 Conference Paper

Learn from Global Rather Than Local: Consistent Context-Aware Representation Learning for Multi-View Graph Clustering

Lele Fu
Bowen Deng
Sheng Huang
Tianchi Liao
Chuanfu Zhang
Chuan Chen

Multi-view graph clustering (MVGC) has been of widespread interest owing to the ability of capturing the complementary information among views, thereby enhancing the performance of node clustering. Despite the impressive achievements of existing methods, they are limited by a common deficiency, namely, the curse of local manifold while failing to perceive the global manifold structure. In light of this drawback, we propose a Consistent Context-Aware Representation Learning (CCARL) method for MVGC, aiming to learn node representations from global space rather than just local topology. Concretely, we define a set of anchors to establish the global coordinate, which are optimally mapped to multi-view graphs with minimal cost via fused Gromov-Wasserstein optimal transport. To fuse the complementary information in various views, the attention mechanism is employed to integrate multiple graph embeddings into a consistent representation. By transforming to the global coordinate connecting with anchors, the consistent representation captures the contextual information, and its clustering-friendliness is further enhanced through a self-training strategy. Finally, extensive experiments on four multi-view graph datasets demonstrate the effectiveness of the proposed CCARL over existing MVGC methods.

PDF Details DOI

EAAI Journal 2025 Journal Article

Prototypical networks with unlabeled data for few-shot node classification

Ningrui Wang
Yujing Lai
Chuan Chen
Zibin Zheng

Due to the high costs of label acquisition in graph, few-shot node classification receives tremendous research interest, which aims to classify unseen labels with limited available nodes given. Although numerous works on few-shot learning have emerged, most of them are established for data following independent identical distribution assumption, which is invalid on graphs where nodes are mutually dependent. Moreover, a majority of existing methods for few-shot node classification are trained with only supervised signals provided by the few labeled samples, neglecting the information implied by a substantial amount of unlabeled data. In this paper, we address the problem of few-shot node classification on the graph, presenting that the distribution of unlabeled nodes can also act as a kind of complementary supervised information to guide the model training. Specifically, we propose a prototype based method that exploits the unlabeled data to provide additional supervised signals for both the encoder and the prototype. We construct a hybrid contrastive loss to leverage self-supervised information from graph topology for encoder enhancement. Meanwhile, the prototype is refined with unlabeled nodes for better reflecting the actual properties of the class. Extensive experiments demonstrate that our method significantly outperforms existing approaches, achieving up to 6. 33% higher accuracy and showing superior robustness, with an average performance variation of only 1. 58%.

Details DOI

NeurIPS Conference 2025 Conference Paper

Self-Assembling Graph Perceptrons

Jialong Chen
Tong Wang
Bowen Deng
Luonan Chen
Zibin Zheng
Chuan Chen

Inspired by the workings of biological brains, humans have designed artificial neural networks (ANNs), sparking profound advancements across various fields. However, the biological brain possesses high plasticity, enabling it to develop simple, efficient, and powerful structures to cope with complex external environments. In contrast, the superior performance of ANNs often relies on meticulously crafted architectures, which can make them vulnerable when handling complex inputs. Moreover, overparameterization often characterizes the most advanced ANNs. This paper explores the path toward building streamlined and plastic ANNs. Firstly, we introduce the Graph Perceptron (GP), which extends the most fundamental ANN, the Multi-Layer Perceptron (MLP). Subsequently, we incorporate a self-assembly mechanism on top of GP called Self-Assembling Graph Perceptron (SAGP). During training, SAGP can autonomously adjust the network's number of neurons and synapses and their connectivity. SAGP achieves comparable or even superior performance with only about 5% of the size of an MLP. We also demonstrate the SAGP's advantages in enhancing model interpretability and feature selection.

PDF Details

NeurIPS Conference 2025 Conference Paper

Soft-consensual Federated Learning for Data Heterogeneity via Multiple Paths

Sheng Huang
Lele Fu
Fanghua Ye
Tianchi Liao
Bowen Deng
Chuan Chen

Federated learning enables collaborative training while preserving the privacy of all participants. However, the heterogeneity in data distribution across multiple training nodes poses significant challenges to the construction of federated models. Prior studies were dedicated to mitigating the effects of data heterogeneity by using global information as a blueprint and restricting the local update of the model for reaching a "hard consensus". But this practice makes it difficult to balance local and global information, and it neglects to negotiate amicably between local and global models to reach mutually agreeable results, called ``soft consensus". In this paper, a multiple-path solving method is proposed to balance global and local features and combine these two feature preference paths to reach a soft consensus. Rather than relying on global information as the sole criterion, a negotiation process is employed to address the same objective by accommodating diverse feature preferences, thereby facilitating the discovery of a more plausible solution through multiple distinct pathways. Considering the overwhelming power of local features during local training, a swapping strategy is applied to weaken them to balance the solution paths. Moreover, to minimize the additional communication cost caused by the introduction of multiple paths, the solution of the task network is converted into data adaptation to reduce the amount of parameter transmission. Extensive experiments are conducted to demonstrate the advantages of the proposed method.

PDF Details

AAAI Conference 2025 Conference Paper

THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings

Bowen Deng
Tong Wang
Lele Fu
Sheng Huang
Chuan Chen
Tao Zhang

Graph node clustering is a fundamental unsupervised task. Existing methods typically train an encoder through self-supervised learning and then apply K-means to the encoder output. Some methods use this clustering result directly as the final assignment, while others initialize centroids based on this initial clustering and then finetune both the encoder and these learnable centroids. However, due to their reliance on K-means, these methods inherit its drawbacks when the cluster separability of encoder output is low, facing challenges from the Uniform Effect and Cluster Assimilation. We summarize three reasons for the low cluster separability in existing methods: (1) lack of contextual information prevents discrimination between similar nodes from different clusters; (2) training tasks are not sufficiently aligned with the downstream clustering task; (3) the cluster information in the graph structure is not appropriately exploited. To address these issues, we propose conTrastive grapH clustEring by SwApping fUsed gRomov-wasserstein coUplingS (THESAURUS). Our method introduces semantic prototypes to provide contextual information, and employs a cross-view assignment prediction pretext task that aligns well with the downstream clustering task. Additionally, it utilizes Gromov-Wasserstein Optimal Transport (GW-OT) along with the proposed prototype graph to thoroughly exploit cluster information in the graph structure. To adapt to diverse real-world data, THESAURUS updates the prototype graph and the prototype marginal distribution in OT by using momentum. Extensive experiments demonstrate that THESAURUS achieves higher cluster separability than the prior art, effectively mitigating the Uniform Effect and Cluster Assimilation issues.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Unsupervised Federated Graph Learning

Lele Fu
Tianchi Liao
Sheng Huang
Bowen Deng
Shirui Pan
Chuan Chen

Federated graph learning (FGL) is a privacy-preserving paradigm for modeling distributed graph data, designed to train a powerful global graph neural network. Existing FGL methods predominantly rely on label information during training, effective FGL in an unsupervised setting remains largely unexplored territory. In this paper, we address two key challenges in unsupervised FGL: 1) Local models tend to converge in divergent directions due to the lack of shared semantic information across clients. Then, how to align representation spaces among multiple clients is the first challenge. 2) Conventional federated weighted aggregation easily results in degrading the performance of the global model, then which raises another challenge, namely how to adaptively learn the global model parameters. In response to the two questions, we propose a tailored framework named FedPAM, which is composed of two modules: Representation Space Alignment (RSA) and Adaptive Global Parameter Learning (AGPL). RSA leverages a set of learnable anchors to define the global representation space, then local subgraphs are aligned with them through the fused Gromov-Wasserstein optimal transport, achieving the representation space alignment across clients. AGPL stacks local model parameters into third-order tensors, and adaptively integrates the global model parameters in a low-rank tensor space, which facilitates to fuse the high-order knowledge among clients. Extensive experiments on eight graph datasets are conducted, the results demonstrate that the proposed FedPAM is superior over classical and SOTA compared methods.

PDF Details

NeurIPS Conference 2024 Conference Paper

A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm

Tianchi Liao
Lele Fu
Jialong Chen
Zhen Wang
Zibin Zheng
Chuan Chen

The heterogeneity issue in federated learning (FL) has attracted increasing attention, which is attempted to be addressed by most existing methods. Currently, due to systems and objectives heterogeneity, enabling clients to hold models of different architectures and tasks of different demands has become an important direction in FL. Most existing FL methods are based on the homogeneity assumption, namely, different clients have the same architectural models with the same tasks, which are unable to handle complex and multivariate data and tasks. To flexibly address these heterogeneity limitations, we propose a novel federated multi-task learning framework with the help of tensor trace norm, FedSAK. Specifically, it treats each client as a task and splits the local model into a feature extractor and a prediction head. Clients can flexibly choose shared structures based on heterogeneous situations and upload them to the server, which learns correlations among client models by mining model low-rank structures through tensor trace norm. Furthermore, we derive convergence and generalization bounds under non-convex settings. Evaluated on 6 real-world datasets compared to 13 advanced FL models, FedSAK demonstrates superior performance.

PDF Details DOI

EAAI Journal 2023 Journal Article

Dual objective bounded abstaining model to control performance for safety-critical applications

Hongjiao Guan
Xiangjun Dong
Chuan Chen
Long Zhao
Xiaoqiang Ren

Abstaining models have been widely used in safety-critical fields to avoid uncertain classification and reduce misclassification costs. Previous abstaining models have two main disadvantages. First, the costs of classification and rejection need to be set. Unfortunately, it is difficult to obtain or estimate costs in practical applications. When costs change, the trained model will be no longer applicable. Second, a single indicator, such as the error rate or AUC, is optimized, which has poor robustness for different application requirements. To solve such problems, a dual objective bounded abstaining (DOBA) model is proposed. DOBA optimizes the binary confusion matrix with rejection by minimizing the false positive and negative rates under class-specific reject constraints. The DOBA model is solved using an evolutionary multi-objective optimization algorithm. The requirement-oriented abstaining classifier can be selected from a set of Pareto-optimal solutions. Extensive experiments prove the effectiveness and superiority of DOBA compared to other abstaining models.

Details DOI

EAAI Journal 2023 Journal Article

Extended natural neighborhood for SMOTE and its variants in imbalanced classification

Hongjiao Guan
Long Zhao
Xiangjun Dong
Chuan Chen

Imbalanced data classification is a challenging issue encountered in many practical applications. Synthetic minority oversampling technique (SMOTE) and its variants are popular resampling methods. However, in most of these methods, the neighborhood determined by k -nearest neighbor ( k NN) cannot reflect the local distribution precisely, leading to the generation of noisy examples. To solve this problem, we propose a neighborhood concept without parameter k called extended natural neighbor (ENaN), which is derived from natural neighbor (NaN). ENaN unites k NN and reverse k NN to determine neighbors adaptively according to the sample distribution. Compared to NaN, ENaN explores broad neighborhoods, which facilitates to improve the quality of generated examples. ENaN-based SMOTE (ENaNSMOTE) can improve the sample distribution obtained by SMOTE and NaNSMOTE. Extensive experiments using 30 synthetic and 20 real-world datasets prove the effectiveness of ENaN in SMOTE and its variants.

Details DOI

AIIM Journal 2020 Journal Article

Implementation of artificial intelligence in medicine: Status analysis and development suggestions

Yifan Xiang
Lanqin Zhao
Zhenzhen Liu
Xiaohang Wu
Jingjing Chen
Erping Long
Duoru Lin
Yi Zhu

The general public’s attitudes, demands, and expectations regarding medical AI could provide guidance for the future development of medical AI to satisfy the increasing needs of doctors and patients. The objective of this study is to investigate public perceptions, receptivity, and demands regarding the implementation of medical AI. An online questionnaire was designed to investigate the perceptions, receptivity, and demands of general public regarding medical AI between October 13 and October 30, 2018. The distributions of the current achievements, public perceptions, receptivity, and demands among individuals in different lines of work (i. e. , healthcare vs non-healthcare) and different age groups were assessed by performing descriptive statistics. The factors associated with public receptivity of medical AI were assessed using a linear regression model. In total, 2, 780 participants from 22 provinces were enrolled. Healthcare workers accounted for 54. 3 % of all participants. There was no significant difference between the healthcare workers and non-healthcare workers in the high proportion (99 %) of participants expressing acceptance of AI (p = 0. 8568), but remarkable distributional differences were observed in demands (p < 0. 001 for both demands for AI assistance and the desire for AI improvements) and perceptions (p < 0. 001 for safety, validity, trust, and expectations). High levels of receptivity (approximately 100 %), demands (approximately 80 %), and expectations (100 %) were expressed among different age groups. The receptivity of medical AI among the non-healthcare workers was associated with gender, educational qualifications, and demands and perceptions of AI. There was a very large gap between current availability of and public demands for intelligence services (p < 0. 001). More than 90 % of healthcare workers expressed a willingness to devote time to learning about AI and participating in AI research. The public exhibits a high level of receptivity regarding the implementation of medical AI. To date, the achievements have been rewarding, and further advancements are required to satisfy public demands. There is a strong demand for intelligent assistance in many medical areas, including imaging and pathology departments, outpatient services, and surgery. More contributions are imperative to facilitate integrated and advantageous implementation in medical AI.

Details DOI

IJCAI Conference 2019 Conference Paper

Dynamically Route Hierarchical Structure Representation to Attentive Capsule for Text Classification

Wanshan Zheng
Zibin Zheng
Hai Wan
Chuan Chen

Representation learning and feature aggregation are usually the two key intermediate steps in natural language processing. Despite deep neural networks have shown strong performance in the text classification task, they are unable to learn adaptive structure features automatically and lack of a method for fully utilizing the extracted features. In this paper, we propose a novel architecture that dynamically routes hierarchical structure feature to attentive capsule, named HAC. Specifically, we first adopt intermediate information of a well-designed deep dilated CNN to form hierarchical structure features. Different levels of structure representations are corresponding to various linguistic units such as word, phrase and clause, respectively. Furthermore, we design a capsule module using dynamic routing and equip it with an attention mechanism. The attentive capsule implements an effective aggregation strategy for feature clustering and selection. Extensive results on eleven benchmark datasets demonstrate that the proposed model obtains competitive performance against several state-of-the-art baselines. Our code is available at https: //github. com/zhengwsh/HAC.

PDF Details

AAAI Conference 2019 Conference Paper

Tensor Decomposition for Multilayer Networks Clustering

Zitai Chen
Chuan Chen
Zibin Zheng
Yi Zhu

Clustering on multilayer networks has been shown to be a promising approach to enhance the accuracy. Various multilayer networks clustering algorithms assume all networks derive from a latent clustering structure, and jointly learn the compatible and complementary information from different networks to excavate one shared underlying structure. However, such an assumption is in conflict with many emerging real-life applications due to the existence of noisy/irrelevant networks. To address this issue, we propose Centroid-based Multilayer Network Clustering (CMNC), a novel approach which can divide irrelevant relationships into different network groups and uncover the cluster structure in each group simultaneously. The multilayer networks is represented within a unified tensor framework for simultaneously capturing multiple types of relationships between a set of entities. By imposing the rank-(Lr, Lr, 1) block term decomposition with nonnegativity, we are able to have well interpretations on the multiple clustering results based on graph cut theory. Numerically, we transform this tensor decomposition problem to an unconstrained optimization, thus can solve it efficiently under the nonlinear least squares (NLS) framework. Extensive experimental results on synthetic and real-world datasets show the effectiveness and robustness of our method against noise and irrelevant data.

PDF Details

IJCAI Conference 2019 Conference Paper

Variational Graph Embedding and Clustering with Laplacian Eigenmaps

Zitai Chen
Chuan Chen
Zong Zhang
Zibin Zheng
Qingsong Zou

As a fundamental machine learning problem, graph clustering has facilitated various real-world applications, and tremendous efforts had been devoted to it in the past few decades. However, most of the existing methods like spectral clustering suffer from the sparsity, scalability, robustness and handling high dimensional raw information in clustering. To address this issue, we propose a deep probabilistic model, called Variational Graph Embedding and Clustering with Laplacian Eigenmaps (VGECLE), which learns node embeddings and assigns node clusters simultaneously. It represents each node as a Gaussian distribution to disentangle the true embedding position and the uncertainty from the graph. With a Mixture of Gaussian (MoG) prior, VGECLE is capable of learning an interpretable clustering by the variational inference and generative process. In order to learn the pairwise relationships better, we propose a Teacher-Student mechanism encouraging node to learn a better Gaussian from its instant neighbors in the stochastic gradient descent (SGD) training fashion. By optimizing the graph embedding and the graph clustering problem as a whole, our model can fully take the advantages in their correlation. To our best knowledge, we are the first to tackle graph clustering in a deep probabilistic viewpoint. We perform extensive experiments on both synthetic and real-world networks to corroborate the effectiveness and efficiency of the proposed framework.

PDF Details