NeurocomputingPub Date : 2025-03-22DOI: 10.1016/j.neucom.2025.130029
Yao Liang , Jian Shu , Linlan Liu
{"title":"Attributed network community detection based on graph contrastive learning and multi-objective evolutionary algorithm","authors":"Yao Liang , Jian Shu , Linlan Liu","doi":"10.1016/j.neucom.2025.130029","DOIUrl":"10.1016/j.neucom.2025.130029","url":null,"abstract":"<div><div>Attributed network community detection holds significant research value for network structure analysis and practical applications. However, existing methods still face significant challenges in addressing the conflicts between topological structure and attribute features, as well as balancing structural tightness and attribute similarity in community detection. In light of this, we propose a community detection method based on graph contrastive learning and multi-objective evolutionary algorithm (GCL-MOEA) for attributed networks. Specifically, GCL-MOEA contains two core parts: node embedding and community detection. Considering the conflict between topological structure and attribute features, the node embedding part constructs topology-augmented and attribute-augmented views, which are utilized in a cross-view graph contrastive learning model. This model comprehensively extracts node features to obtain node embedding vectors, effectively preserving the consistency and complementarity between the structure and attributes. The community detection part utilizes clustering results of node embeddings to construct high-quality initial populations. A multi-objective evolutionary algorithm is subsequently employed to obtain community structures where nodes are tightly connected and have similar attributes. The effectiveness of the proposed method is validated on five real-world networks. Experimental results demonstrate that GCL-MOEA outperforms baselines in terms of ACC, NMI, ARI, and F1, obtaining better community detection results.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130029"},"PeriodicalIF":5.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NeurocomputingPub Date : 2025-03-20DOI: 10.1016/j.neucom.2025.129968
Xin Huang , Sicheng Bi , Xinyu Han , Shuyi Xiao , Qingyu Su
{"title":"An event-triggered reliable cloud control scheme based on ADP and integral sliding mode","authors":"Xin Huang , Sicheng Bi , Xinyu Han , Shuyi Xiao , Qingyu Su","doi":"10.1016/j.neucom.2025.129968","DOIUrl":"10.1016/j.neucom.2025.129968","url":null,"abstract":"<div><div>This paper investigates event-triggered (ET) reliable control problems for cloud control systems under actuator faults and data injection attacks via the adaptive dynamic programming (ADP) and integral sliding mode (ISM). A mist-fog-regional cloud control architecture is first given, which can improve computing efficiency of the cloud platform. In this architecture, a fog-based fault parameter estimation method is proposed with the aid of neural networks. It is driven by the feedback of fault parameter estimation errors, so as to achieve more accurate estimations of fault parameters. A double ET reliable cloud control scheme is further presented. It is composed of an ISM-based and an ADP-based regional cloud controllers. As a result, it not only saves communication resources, but also eliminates the influence of the attacks and matched uncertainties, as well as ensures the stability of the equivalent sliding-mode dynamics with optimal performance. Finally, the effectiveness of the proposed method is verified by the simulation results.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 129968"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143686895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NeurocomputingPub Date : 2025-03-20DOI: 10.1016/j.neucom.2025.129991
Adam Callaghan, Karl Mason, Patrick Mannion
{"title":"Extending Evolution-Guided Policy Gradient Learning into the multi-objective domain","authors":"Adam Callaghan, Karl Mason, Patrick Mannion","doi":"10.1016/j.neucom.2025.129991","DOIUrl":"10.1016/j.neucom.2025.129991","url":null,"abstract":"<div><div>Multi-Objective Reinforcement Learning (MORL) poses significant challenges, primarily due to the necessity of balancing conflicting objectives—a limitation that traditional single-objective approaches fail to address. This paper introduces Multi-Objective Evolutionary Reinforcement Learning (MO-ERL), the first adaptation of Evolutionary Reinforcement Learning (ERL) specifically designed to address the complexities of the multi-objective domain effectively.</div><div>MO-ERL integrates policy gradient-based reinforcement learning (RL), which optimizes expected utility, with evolutionary algorithms (EAs) that maintain diversity across the Pareto front. This combination leverages RL’s strength in exploitation and EAs’ proficiency in exploration, enabling MO-ERL to effectively navigate the trade-offs inherent in multi-objective optimization problems.</div><div>Evaluation on multi-objective continuous control tasks using the MuJoCo physics engine demonstrates that MO-ERL outperforms state-of-the-art baselines, achieving up to 62.71% higher hypervolume and 196.28% greater expected utility. These results validate MO-ERL’s ability to balance solution diversity and optimality, setting a new benchmark for solving MORL tasks.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 129991"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"L2M-GCN: A new framework for learning robust GCN against structural attacks","authors":"Haoran Chen , Xianchen Zhou , Jiwei Zhang , Hongxia Wang","doi":"10.1016/j.neucom.2025.129962","DOIUrl":"10.1016/j.neucom.2025.129962","url":null,"abstract":"<div><div>Graph Convolutional Networks (GCNs) have gained extensive attention due to their strong ability to learn from graphs. However, with the advent of stealthy attacks that cause significant differences in node embeddings, the vulnerability of GCNs to malicious attacks has been exposed. Although there are many studies on defense in the spatial or spectral domains, they neglect the complementary roles of the two. In this paper, we propose a new framework, Low frequency and 2-hop in Multi-channel GCN (L2M-GCN), which combines spatial and spectral defense. L2M-GCN has two GCN-based modules. In module one, a new structure reconstructed from learnable spectrum and low-frequency components replaces the adjacency matrix in GCN. In module two, purified 2-hop is introduced and the attention mechanism is used to learn the importance weights of node embeddings. The two modules are eventually assembled into L2M-GCN for joint learning in a parameter-sharing and end-to-end fashion. Extensive experiments demonstrate that L2M-GCN significantly improves the defense performance against structural attacks and outperforms the baselines and state-of-the-art methods.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 129962"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Real-time stereo matching with enhanced geometric comprehension through cross-attention integration","authors":"Hosein Hashemi, Yasser Baleghi, Mohamad Reza Hassanzadeh","doi":"10.1016/j.neucom.2025.130069","DOIUrl":"10.1016/j.neucom.2025.130069","url":null,"abstract":"<div><div>Accurate disparity estimation through stereo matching remains a critical challenge, especially for real-time applications. This work introduces a novel and computationally efficient framework that achieves high accuracy and real-time performance in stereo-based disparity estimation. The proposed approach introduces three key innovations. This work proposes a context cross-attention (CCA) module, which enhances the cost volume aggregation process by leveraging localized cross-attention for improved geometric understanding. Guided concatenation volume (GCV) is also implemented, which optimizes feature matching by effectively combining correlation clues with contextual information, reducing computational redundancy while maintaining crucial spatial details. Also, this paper proposes an uncertainty-based refinement (UR) module, which improves accuracy in challenging scenarios by utilizing an uncertainty map, a context feature map, and a geometry feature map to correct errors in challenging areas such as textureless regions and occlusions. Comprehensive experiments on multiple benchmark datasets, including KITTI, Sceneflow, Middlebury, and ETH3D, demonstrate that the proposed model performs better than existing state-of-the-art real-time approaches in accuracy metrics while maintaining comparable computational efficiency. These results establish the framework as a viable solution for demanding real-world applications, particularly in autonomous driving and robotics systems where real-time performance is crucial. The source code is available at <span><span>https://github.com/kayhan-hashemi/CCAStereo</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130069"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NeurocomputingPub Date : 2025-03-20DOI: 10.1016/j.neucom.2025.130001
Junsheng Yu , Huizhi Xu , Zhongjun Ma
{"title":"Lag-bipartite consensus control of nonlinear multi-agent systems with exogenous disturbances via dynamic event-triggered strategy","authors":"Junsheng Yu , Huizhi Xu , Zhongjun Ma","doi":"10.1016/j.neucom.2025.130001","DOIUrl":"10.1016/j.neucom.2025.130001","url":null,"abstract":"<div><div>This paper explores the lag-bipartite consensus issue for nonlinear multi-agent systems with external disturbances via event-triggered mechanisms. Firstly, a disturbance observer is devised to offset disturbances induced from ambient noise or parameter uncertainties. To save needless communication among neighbor agents and enhance the system’s anti-disturbance abilities, the centralized event-based approach and a distributed dynamic event-triggered control scheme with internal dynamic parameters are raised via combining the disturbance compensation strategy, respectively. Unlike existent static triggering approaches, this dynamic triggering scheme widens interval duration between two successive triggering instants. On the basis of both control schemes, a few sufficient conditions are provided to reach lag-bipartite consensus for nonlinear multi-agent systems, while Zeno behavior cannot arise via developed triggering rules. Finally, the validity of presented schemes is illustrated under numerical examples.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130001"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NeurocomputingPub Date : 2025-03-20DOI: 10.1016/j.neucom.2025.129992
Qing Pan, Zirong Zhang, Nili Tian
{"title":"Zero-reference generative exposure correction and adaptive fusion for low-light image enhancement","authors":"Qing Pan, Zirong Zhang, Nili Tian","doi":"10.1016/j.neucom.2025.129992","DOIUrl":"10.1016/j.neucom.2025.129992","url":null,"abstract":"<div><div>Existing low-light image enhancement methods have the problem of difficulty in enhancing dark areas while controlling overexposed areas in natural images. To address this issue, a Generative Exposure Correction method based on Retinex theory is proposed in this paper, in which the Pseudo-Exposure Residual map and illumination map are deeply coupled based on the proposed intensity compensation prior to constrain the generative network’s output in order to simultaneously deal with overexposure and underexposure. Furthermore, to enhance the effect and prevent over-correction, an exposure fusion technique is proposed, which adaptively selects the best exposure area from the two corrected images and achieves a globally balanced exposure by using an intensity correction compensation operator. More importantly, our proposed method does not require the collection of additional external datasets, which also overcomes the difficulty of data acquisition. Experimental comparisons of our method with the other seven state-of-the-art methods on five public datasets demonstrate that our method achieves the best performance in terms of detail enhancement and natural color preservation.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 129992"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NeurocomputingPub Date : 2025-03-20DOI: 10.1016/j.neucom.2025.130008
Yilin Wang , Sha Zhao , Haiteng Jiang , Shijian Li , Tao Li , Gang Pan
{"title":"M-MDD: A multi-task deep learning framework for major depressive disorder diagnosis using EEG","authors":"Yilin Wang , Sha Zhao , Haiteng Jiang , Shijian Li , Tao Li , Gang Pan","doi":"10.1016/j.neucom.2025.130008","DOIUrl":"10.1016/j.neucom.2025.130008","url":null,"abstract":"<div><div>Major depressive disorder (MDD) is a common and destructive psychiatric disorder worldwide. Traditional MDD diagnosis relies heavily on subjective observation and questionnaires. Recently, a non-invasive method of recording the brain’s spontaneous activity called Electroencephalogram (EEG) has been a useful tool of MDD diagnosis. However, there are still some challenges to be addressed: (1) The model’s robustness to common EEG noise has to be improved, (2) The temporal, spectral and spatial features of EEG need to be extracted and fused appropriately. Learning both robust and powerful features for MDD diagnosis can improve the overall performance, and multi-task learning is a powerful solution. In this paper, we propose M-MDD, a multi-task deep learning framework for MDD diagnosis using EEG. First, we design the Contrastive Noise Robustness Task to learn noise-independent features. Then, we design the Supervised Feature Extraction Task to extract temporal, spectral and spatial features of EEG respectively, and then effectively combine them together. Finally, the above two modules share the same feature space and are trained jointly with the Multi-task Learning Module, improving the overall performance. Validated on two public MDD diagnosis datasets with subject-independent cross-validation, our model achieves the state-of-the-art performance.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130008"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NeurocomputingPub Date : 2025-03-20DOI: 10.1016/j.neucom.2025.130007
Xiaotian Wang , Xiang Jiang , Zhifu Zhao , Kexin Wang , Yifan Yang
{"title":"Exploring interaction: Inner-outer spatial–temporal transformer for skeleton-based mutual action recognition","authors":"Xiaotian Wang , Xiang Jiang , Zhifu Zhao , Kexin Wang , Yifan Yang","doi":"10.1016/j.neucom.2025.130007","DOIUrl":"10.1016/j.neucom.2025.130007","url":null,"abstract":"<div><div>Transformer-based methods have achieved significant results in the field of skeleton-based action recognition. However, when dealing with two-person interaction, existing approaches normally embed the skeleton of each person separately and then introduce an additional module to learn their interactions. This risks losing the spatial and semantic connection information between the two entities, which is crucial for interaction identification. To address this issue, a unified interactive spatial–temporal transformer is proposed in this paper. First, a Two-Person Embedding (TPE) is performed to provide a holistic interactive relationship representation, which can effectively avoid the information gap caused by the division of interacting entities. Second, an innovative Inner-Outer Transformer (IOformer) combining with a new spatio-temporal partition strategy is proposed to simultaneously learn the interactions between intra-partition joints and inter-partition skeletal parts. By comprehensively capturing the key spatio-temporal interactive feature, the accuracy and robustness of interaction recognition can be significantly improved. Extensive experiments on three challenging benchmark datasets validate that our method achieves better performance in comprehensive evaluation methods.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130007"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NeurocomputingPub Date : 2025-03-20DOI: 10.1016/j.neucom.2025.130009
Ruiqi Zha, Zhichao Lian, Qianmu Li
{"title":"Centroid-based Contrastive Consistency Learning for transferable deepfake detection","authors":"Ruiqi Zha, Zhichao Lian, Qianmu Li","doi":"10.1016/j.neucom.2025.130009","DOIUrl":"10.1016/j.neucom.2025.130009","url":null,"abstract":"<div><div>Previous research efforts in deepfake detection mainly concentrated on identifying and differentiating artifacts discernible to humans. Those methods have left a bias in learned models, as they tend to concentrate on the disparities between forged and natural regions from the perspective of a single sample while overlooking consistency within categories from the perspective of the entire sample set, which remains crucial across various real-world applications. Therefore, inspired by contrastive learning, we tackle the deepfake detection problem by learning the invariant representations of both categories. Our proposed method, termed Centroid-based Contrastive Consistency Learning (C3L) method, integrates constraints on representations at both the data preprocessing and feature extraction stages. Specifically, during data preprocessing, we consider both temporal relationships within videos and the latent relationships within synthesis data. We introduce a novel Positive Enhancement Module (PEM) designed to characterize natural and forged samples in a facial semantically irrelevant way, thereby guiding a task-oriented positive pair contrasting strategy. In addition, at the feature extraction stage, we introduce the Margin Feature Simulation Module (MFSM), which leverages the centroid of the natural category to simulate marginal features for both categories. Subsequently, we employ the Supervised Contrastive Margin Loss (SCML), utilizing simulated features to emphasize differences at decision boundaries and optimize the learning process. The effectiveness and robustness of the proposed method have been demonstrated through extensive experiments.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"637 ","pages":"Article 130009"},"PeriodicalIF":5.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}