Author name cluster

Badong 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.

17 papers

2 author rows

EAAI Journal 2026 Journal Article

A dual-stream regional feature learning and adaptive fusion method for electroencephalogram-based emotion recognition

Yong Yang
Wenhao Wang
Kaibo Shi
Yuanlun Xie
Nan Zhou
Shiping Wen
Ming Zhu
Badong Chen

Electroencephalogram (EEG) has become a research hotspot in emotion recognition due to its high temporal resolution and ability to truly reflect brain activity. However, few existing EEG-based emotion recognition methods integrate brain region information into the algorithm and do not fully extract the deep features of each region. Brain science has shown that different brain regions have different functions and are highly correlated with the production of emotions. In this paper, based on the division of brain regions, a dual-branch regional feature learning and adaptive fusion neural network (DRFNet) is proposed to extract the features of different brain regions and adaptively fuse regional features, thereby achieving accurate EEG emotion recognition. Specifically, DRFNet mainly consists of regional feature extraction modules (DB-CTFEM) and a feature fusion module (RFM). The DB-CTFEM extracts regional local and global features through the dual-branch structure of convolutional neural network (CNN) and Transformer, respectively, and then uses cross-attention to effectively fuse the two to obtain enhanced regional features. Considering the differences of brain regions, RFM uses the attention mechanism to fuse regional features and adaptively reconstruct global brain features. In addition, a region loss function based on the importance of region features is proposed to dynamically adjust the contribution weights of different brain regions, thereby guiding the model to pay more attention to key regions. This paper conducts subject-dependent experiments on the SJTU Emotion EEG Datasets (SEED, SEED-IV, SEED-V, and SEED-VII) to verify effectiveness and robustness of the proposed method.

Details DOI

EAAI Journal 2026 Journal Article

Correntropy meets cross-entropy: A robust loss against noisy labels

Nan Zhou
Qing Deng
Wenjun Luo
Xiuyu Huang
Yuanhua Du
Badong Chen
Witold Pedrycz

Noisy labels are a common challenge in real-world datasets, severely degrading the training of deep learning models. Enhancing the robustness of the loss function offers a flexible solution to mitigate this issue. This study first demonstrates that Categorical Cross-Entropy (CE), one of the most popular choices used to train a classification model, leads to significant performance degradation. To alleviate this issue, we innovatively propose a novel loss function called Correntropy-Inspired Cross-Entropy (CICE) loss, which utilizes the properties of correntropy and is robust to noisy labels. Compared with CE, CICE retains CE’s core functionality for linear class separation while automatically alleviating the adverse effects of noisy labels during training. Extensive experiments on four public datasets across multiple scenarios with varying noisy label rates validate CICE’s effectiveness. Results show that CICE outperforms 13 state-of-the-art loss functions in noise resilience and classification accuracy, establishing its superiority in noisy-label environments.

Details DOI

EAAI Journal 2026 Journal Article

Reactive power optimization under risk-aware demand response: Attentive gated recurrent unit and safe dual-critic architecture

Xinghua Liu
Xiaoyu Wang
Bangji Fan
Zhengmao Li
Gaoxi Xiao
Shiping Wen
Badong Chen

The uncertain fluctuations of renewable energy sources and the diverse composition of user loads pose significant challenges for the optimal control of reactive power in active distribution networks (ADNs). Most previous studies have focused solely on scheduling multiple types of grid-side reactive power devices to formulate dispatch strategies, which does not reflect current practice. To incorporate the scheduling potential of customer-side resources, this paper proposes a risk-aware multi-agent graph reinforcement learning framework for coordinated reactive power management in ADNs under demand response. We reformulate the reactive power optimization problem as a multi-agent constrained Markov decision process (CMDP) by introducing voltage security constraints. Three agents are defined to control photovoltaic inverters (PVs), capacitor banks (CBs), and dispatchable loads, respectively. To capture the network’s non-Euclidean topology and temporal dynamics, we integrate a graph attention-gated recurrent composite unit into the Soft Actor–Critic (SAC) architecture, thereby enhancing spatiotemporal feature extraction. Moreover, we introduce the Parameterized Huber loss function to smooth Q-value estimation and improve training stability. Case studies based on real distribution network data verify the effectiveness of the proposed method. Comparative experiments against baseline algorithms – such as SAC, Deep Deterministic Policy Gradient (DDPG), and Twin Delayed DDPG (TD3) – demonstrate superior convergence performance and consistent voltage security.

Details DOI

ICLR Conference 2025 Conference Paper

Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency

Jiangrong Shen
Qi Xu 0008
Gang Pan 0001
Badong Chen

The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its lifespan. Drawing inspiration from this spike-based computation, Spiking Neural Networks (SNNs) have been developed to construct event-driven models that emulate this efficiency. Despite these advances, deep SNNs continue to suffer from over-parameterization during training and inference, a stark contrast to the brain’s ability to self-organize. Furthermore, existing sparse SNNs are challenged by maintaining optimal pruning levels due to a static pruning ratio, resulting in either under or over-pruning. In this paper, we propose a novel two-stage dynamic structure learning approach for deep SNNs, aimed at maintaining effective sparse training from scratch while optimizing compression efficiency. The first stage evaluates the compressibility of existing sparse subnetworks within SNNs using the PQ index, which facilitates an adaptive determination of the rewiring ratio for synaptic connections based on data compression insights. In the second stage, this rewiring ratio critically informs the dynamic synaptic connection rewiring process, including both pruning and regrowth. This approach significantly improves the exploration of sparse structures training in deep SNNs, adapting sparsity dynamically from the point view of compression efficiency. Our experiments demonstrate that this sparse training approach not only aligns with the performance of current deep SNNs models but also significantly improves the efficiency of compressing sparse SNNs. Crucially, it preserves the advantages of initiating training with sparse models and offers a promising solution for implementing Edge AI on neuromorphic hardware.

Details

NeurIPS Conference 2025 Conference Paper

Local-Global Coupling Spiking Graph Transformer for Brain Disorders Diagnosis from Two Perspectives

Geng Zhang
Jiangrong Shen
Kaizhong Zheng
Liangjun Chen
Badong Chen

Brain disorders have been consistently associated with abnormalities in specific brain regions or neural circuits. Identifying key brain regional activities and functional connectivity patterns is essential for discovering more precise neurobiological biomarkers. However, previous studies have primarily emphasized alterations in functional connectivity while overlooking abnormal neuronal population activity within brain regions. To bridge this gap, we propose a novel Local-Global Coupling Spiking Graph Transformer (LGC-SGT) that jointly models both inter-regional connectivity differences and deviations in neuronal population firing rates within brain regions, enabling a dual-perspective neuropathological analysis. The global pathway leverages spike-based computation in LGC-SGT to model biologically plausible aberrant neural firing dynamics, while the local pathway adaptively captures abnormal graph-based representations of brain connectivity learned by local plasticity in the liquid state machine module. Furthermore, we design a shortcut-enhanced output strategy in LGC-SGT with the hybrid loss function to suppress outlier interference caused by inter-individual and inter-center variability, enabling a more robust decision boundary. Extensive experiments on three brain disorder datasets demonstrate that our model consistently outperforms state-of-the-art graph methods in brain disorder diagnosis. Moreover, it facilitates the extraction of interpretable neurobiological biomarkers by jointly analyzing regional neural activity and functional connectivity, offering a more comprehensive framework for brain disorder understanding and diagnosis.

PDF Details

ICML Conference 2025 Conference Paper

Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation

Shuanghao Bai
Wanqi Zhou
Pengxiang Ding
Wei Zhao
Donglin Wang
Badong Chen

Behavior Cloning (BC) is a widely adopted visual imitation learning method in robot manipulation. Current BC approaches often enhance generalization by leveraging large datasets and incorporating additional visual and textual modalities to capture more diverse information. However, these methods overlook whether the learned representations contain redundant information and lack a solid theoretical foundation to guide the learning process. To address these limitations, we adopt an information-theoretic perspective and introduce mutual information to quantify and mitigate redundancy in latent representations. Building on this, we incorporate the Information Bottleneck (IB) principle into BC, which extends the idea of reducing redundancy by providing a structured framework for compressing irrelevant information while preserving task-relevant features. This work presents the first comprehensive study on redundancy in latent representations across various methods, backbones, and experimental settings, while extending the generalizability of the IB to BC. Extensive experiments and analyses on the CortexBench and LIBERO benchmarks show consistent performance improvements with IB across various settings, underscoring the importance of reducing input data redundancy and highlighting its practical value for real-world applications.

Details

YNIMG Journal 2024 Journal Article

BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping

Kaizhong Zheng
Shujian Yu
Liangjun Chen
Lujuan Dang
Badong Chen

Converging evidence increasingly suggests that psychiatric disorders, such as major depressive disorder (MDD) and autism spectrum disorder (ASD), are not unitary diseases, but rather heterogeneous syndromes that involve diverse, co-occurring symptoms and divergent responses to treatment. This clinical heterogeneity has hindered the progress of precision diagnosis and treatment effectiveness in psychiatric disorders. In this study, we propose BPI-GNN, a new interpretable graph neural network (GNN) framework for analyzing functional magnetic resonance images (fMRI), by leveraging the famed prototype learning. In addition, we introduce a novel generation process of prototype subgraph to discover essential edges of distinct prototypes and employ total correlation (TC) to ensure the independence of distinct prototype subgraph patterns. BPI-GNN can effectively discriminate psychiatric patients and healthy controls (HC), and identify biological meaningful subtypes of psychiatric disorders. We evaluate the performance of BPI-GNN against 11 popular brain network classification methods on three psychiatric datasets and observe that our BPI-GNN always achieves the highest diagnosis accuracy. More importantly, we examine differences in clinical symptom profiles and gene expression profiles among identified subtypes and observe that our identified brain-based subtypes have the clinical relevance. It also discovers the subtype biomarkers that align with current neuro-scientific knowledge.

Details DOI

JBHI Journal 2024 Journal Article

Classification of Three Anesthesia Stages Based on Near-Infrared Spectroscopy Signals

Zhian Liu
Lichengxi Si
Shaoxian Shi
Jing Li
Jing Zhu
Won Hee Lee
Sio-Long Lo
Xiangguo Yan

Proper monitoring of anesthesia stages can guarantee the safe performance of clinical surgeries. In this study, different anesthesia stages were classified using near-infrared spectroscopy (NIRS) signals with machine learning. The cerebral hemodynamic variables of right proximal oxyhemoglobin (HbO 2 ) in maintenance (MNT), emergence (EM) and the consciousness (CON) stage were collected and then the differences between the three stages were compared by phase-amplitude coupling (PAC). Then combined with time-domain including linear (mean, standard deviation, max, min and range), nonlinear (sample entropy) and power in frequency-domain signal features, feature selection was performed and finally classification was performed by support vector machine (SVM) classifier. The results show that the PAC of the NIRS signal was gradually enhanced with the deepening of anesthesia level. A good three-classification accuracy of 69. 27% was obtained, which exceeded the result of classification of any single category feature. These results indicate the feasibility of NIRS signals in performing three or even more anesthesia stage classifications, providing insight into the development of new anesthesia monitoring modalities.

Details DOI

ICML Conference 2024 Conference Paper

Jacobian Regularizer-based Neural Granger Causality

Wanqi Zhou
Shuanghao Bai
Shujian Yu
Qibin Zhao
Badong Chen

With the advancement of neural networks, diverse methods for neural Granger causality have emerged, which demonstrate proficiency in handling complex data, and nonlinear relationships. However, the existing framework of neural Granger causality has several limitations. It requires the construction of separate predictive models for each target variable, and the relationship depends on the sparsity on the weights of the first layer, resulting in challenges in effectively modeling complex relationships between variables as well as unsatisfied estimation accuracy of Granger causality. Moreover, most of them cannot grasp full-time Granger causality. To address these drawbacks, we propose a J acobian R egularizer-based N eural G ranger C ausality ( JRNGC ) approach, a straightforward yet highly effective method for learning multivariate summary Granger causality and full-time Granger causality by constructing a single model for all target variables. Specifically, our method eliminates the sparsity constraints of weights by leveraging an input-output Jacobian matrix regularizer, which can be subsequently represented as the weighted causal matrix in the post-hoc analysis. Extensive experiments show that our proposed approach achieves competitive performance with the state-of-the-art methods for learning summary Granger causality and full-time Granger causality while maintaining lower model complexity and high scalability.

Details

NeurIPS Conference 2024 Conference Paper

Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration

Haowen Dou
Lujuan Dang
Zhirong Luan
Badong Chen

Despite the success of Multi-Agent Reinforcement Learning (MARL) algorithms in cooperative tasks, previous works, unfortunately, face challenges in heterogeneous scenarios since they simply disable parameter sharing for agent specialization. Sequential updating scheme was thus proposed, naturally diversifying agents by encouraging agents to learn from preceding ones. However, the exploration strategy in sequential scheme has not been investigated. Benefiting from updating one-by-one, agents have the access to the information from preceding agents. Thus, in this work, we propose to exploit the preceding information to enhance exploration and heterogeneity sequentially. We present Multi-Agent Divergence Policy Optimization (MADPO), equipped with mutual policy divergence maximization framework. We quantify the policy discrepancies between episodes to enhance exploration and between agents to heterogenize agents, termed intra-agent and inter-agent policy divergence. To address the issue that traditional divergence measurements lack stability and directionality, we propose to employ the conditional Cauchy-Schwarz divergence to provide entropy-guided exploration incentives. Extensive experiments show that the proposed method outperforms state-of-the-art sequential updating approaches in two challenging multi-agent tasks with various heterogeneous scenarios. Source code is available at \url{https: //github. com/hwdou6677/MADPO}.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation

Shuanghao Bai
Min Zhang
Wanqi Zhou
Siteng Huang
Zhirong Luan
Donglin Wang
Badong Chen

Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA. However, a major challenge for directly deploying such models on downstream UDA tasks is prompt engineering, which requires aligning the domain knowledge of source and target domains, since the performance of UDA is severely influenced by a good domain-invariant representation. We further propose a Prompt-based Distribution Alignment (PDA) method to incorporate the domain knowledge into prompt learning. Specifically, PDA employs a two-branch prompt-tuning paradigm, namely base branch and alignment branch. The base branch focuses on integrating class-related representation into prompts, ensuring discrimination among different classes. To further minimize domain discrepancy, for the alignment branch, we construct feature banks for both the source and target domains and propose image-guided feature tuning (IFT) to make the input attend to feature banks, which effectively integrates self-enhanced and cross-domain features into the model. In this way, these two branches can be mutually promoted to enhance the adaptation of VLMs for UDA. We conduct extensive experiments on three benchmarks to demonstrate that our proposed PDA achieves state-of-the-art performance. The code is available at https://github.com/BaiShuanghao/Prompt-based-Distribution-Alignment.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Learning to Generate an Unbiased Scene Graph by Using Attribute-Guided Predicate Features

Lei Wang
Zejian Yuan
Badong Chen

Scene Graph Generation (SGG) aims to capture the semantic information in an image and build a structured representation, which facilitates downstream tasks. The current challenge in SGG is to tackle the biased predictions caused by the long-tailed distribution of predicates. Since multiple predicates in SGG are coupled in an image, existing data re-balancing methods cannot completely balance the head and tail predicates. In this work, a decoupled learning framework is proposed for unbiased scene graph generation by using attribute-guided predicate features to construct a balanced training set. Specifically, the predicate recognition is decoupled into Predicate Feature Representation Learning (PFRL) and predicate classifier training with a class-balanced predicate feature set, which is constructed by our proposed Attribute-guided Predicate Feature Generation (A-PFG) model. In the A-PFG model, we first define the class labels of and corresponding visual feature as attributes to describe a predicate. Then the predicate feature and the attribute embedding are mapped into a shared hidden space by a dual Variational Auto-encoder (VAE), and finally the synthetic predicate features are forced to learn the contextual information in the attributes via cross reconstruction and distribution alignment. To demonstrate the effectiveness of our proposed method, our decoupled learning framework and A-PFG model are applied to various SGG models. The empirical results show that our method is substantially improved on all benchmarks and achieves new state-of-the-art performance for unbiased scene graph generation. Our code is available at https://github.com/wanglei0618/A-PFG.

PDF Details DOI

EAAI Journal 2023 Journal Article

Robust one-class classification with support vector data description and mixed exponential loss function

Yunfei Zheng
Shiyuan Wang
Badong Chen

Support vector data description (SVDD) has received a lot of attention due to its outstanding performance to perform one-class classification or novelty detection tasks. However, the same weight is directly imposed on all slack variables in the process of modeling, which may result in degraded learning performance when training data are contaminated by some outliers or mislabeled observations. In this paper, an extended SVDD model is therefore proposed by reformulating the original optimization problem of SVDD with a mixed exponential loss function. Since this loss function can emphasize the importance of the samples that tend to be the target class, and weaken the influence of those tending to be outliers, it can be viewed as a weighted SVDD. However, the weights in the new model are automatically calculated rather than being calculated in advance using some specific manners. To solve the optimization problem of the proposed model effectively, the half-quadratic optimization technique has been adopted to perform the optimization, generating a dynamic optimization algorithm. Meanwhile, the convergence and computational complexity of this dynamic optimization algorithm are analyzed from a theoretical respective. Experimental results on a synthetic data set and some publicly available real world data sets are reported to demonstrate the performance superiority of the new method in comparison with SVDD and other competitive SVDD variants.

Details DOI

ICRA Conference 2021 Conference Paper

Robust Motion Averaging under Maximum Correntropy Criterion

Jihua Zhu
Jie Hu
Huimin Lu 0001
Badong Chen
Zhongyu Li 0002
Yaochen Li

Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem. This method aims to recover global motions from a set of relative motions, where the original method is sensitive to outliers due to using the Frobenius norm error in the optimization. Accordingly, this paper proposes a novel robust motion averaging method based on the maximum correntropy criterion (MCC). Specifically, the correntropy measure is used instead of utilizing Frobenius norm error to improve the robustness of motion averaging against outliers. According to the half-quadratic technique, the correntropy measure based optimization problem can be solved by the alternating minimization procedure, which includes operations of weight assignment and weighted motion averaging. Further, we design a selection strategy of adaptive kernel width to take advantage of correntropy. Experimental results on benchmark data sets illustrate that our method has superior performance on accuracy and robustness for multi-view registration. What’s more, it can be applied to robot mapping.

Details

EAAI Journal 2020 Journal Article

Robust nonnegative matrix factorization with local coordinate constraint for image clustering

Siyuan Peng
Wee Ser
Badong Chen
Lei Sun
Zhiping Lin

Nonnegative matrix factorization (NMF) has attracted increasing attention in data mining and machine learning. However, existing NMF methods have some limitations. For example, some NMF methods seriously suffer from noisy data contaminated by outliers, or fail to preserve the geometric information of the data and guarantee the sparse parts-based representation. To overcome these issues, in this paper, a robust and sparse NMF method, called correntropy based dual graph regularized nonnegative matrix factorization with local coordinate constraint (LCDNMF) is proposed. Specifically, LCDNMF incorporates the geometrical information of both the data manifold and the feature manifold, and the local coordinate constraint into the correntropy based objective function. The half-quadratic optimization technique is utilized to solve the nonconvex optimization problem of LCDNMF, and the multiplicative update rules are obtained. Furthermore, some properties of LCDNMF including the convergence, relation with gradient descent method, robustness, and computational complexity are analyzed. Experiments of clustering demonstrate the effectiveness and robustness of the proposed LCDNMF method in comparison to several state-of-the-art methods on six real world image datasets.

Details DOI

IS Journal 2018 Journal Article

Multivariate Correlation Entropy and Law Discovery in Large Data Sets

Jianji Wang
Nanning Zheng
Badong Chen
Pei Chen
Shitao Chen
Ziyi Liu
Fei-Yue Wang
Bao Xi

Over the past several centuries, many important natural laws have been discovered by scientists, which have not only changed our viewpoints about nature but also affected our lives significantly. Today, automatic discovery of meaningful laws from data beyond two variables becomes an important task of our time. Here, we propose two multivariate correlation measures, namely, the multivariate correlation entropy (MCE) and the multivariate incorrelation entropy (MIE), which can be used to measure the strength of the correlation among multiple variables. Using MIE makes it possible to directly detect linear relations existing in large data sets. In addition, more complicated nonlinear multivariate laws can be discovered using a function dictionary.

Details DOI

EAAI Journal 2017 Journal Article

Robust kernel adaptive filters based on mean p-power error for noisy chaotic time series prediction

Wentao Ma
Jiandong Duan
Weishi Man
Haiquan Zhao
Badong Chen

Two robust kernel adaptive filter (KAF) algorithms, called the kernel least mean p-power (KLMP) and kernel recursive least mean p-power (KRLP), are developed by combining mean p-power error (MPE) criterion and kernel trick for noisy chaotic time series prediction (CTSP). The proposed algorithms employ the MPE to overcome the performance degradation of the CTSP when training data are corrupted by impulsive noises (especially the α-stable noises). First, the KLMP algorithm is proposed by the gradient decent method to improve the robustness of the traditional kernel least mean square (KLMS). Second, the recursion idea and the kernel method are utilized to develop a recursive KAF, namely KRLP, to improve the robustness of the traditional kernel recursive least squares (KRLS). Simulation results show that the proposed algorithms display notable robustness in CTSP when the training data contain different levels of noises, and can perform better in terms of testing MSE than other algorithms.

Details DOI