{"ID":2844563,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.05876","arxiv_id":"2511.05876","title":"MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering","abstract":"In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform weighted fusion of graph structures at the view level, which is a relatively rough strategy. To address this limitation, we present a novel Mixture of Ego-Graphs Contrastive Representation Learning (MoEGCL). It mainly consists of two modules. In particular, we propose an innovative Mixture of Ego-Graphs Fusion (MoEGF), which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion. Additionally, we present the Ego Graph Contrastive Learning (EGCL) module to align the fused representation with the view-specific representation. The EGCL module enhances the representation similarity of samples from the same cluster, not merely from the same sample, further boosting fine-grained graph representation. Extensive experiments demonstrate that MoEGCL achieves state-of-the-art results in deep multi-view clustering tasks. The source code is publicly available at https://github.com/HackerHyper/MoEGCL.","short_abstract":"In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform w...","url_abs":"https://arxiv.org/abs/2511.05876","url_pdf":"https://arxiv.org/pdf/2511.05876v5","authors":"[\"Jian Zhu\",\"Xin Zou\",\"Jun Sun\",\"Cheng Luo\",\"Lei Liu\",\"Lingfang Zeng\",\"Ning Zhang\",\"Bian Wu\",\"Chang Tang\",\"Lirong Dai\"]","published":"2025-11-08T06:27:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false,"code_links":[{"ID":607308,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2844563,"paper_url":"https://arxiv.org/abs/2511.05876","paper_title":"MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering","repo_url":"https://github.com/HackerHyper/MoEGCL","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}