{"ID":2898880,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.02847","arxiv_id":"2507.02847","title":"MvHo-IB: Multi-View Higher-Order Information Bottleneck for Brain Disorder Diagnosis","abstract":"Recent evidence suggests that modeling higher-order interactions (HOIs) in functional magnetic resonance imaging (fMRI) data can enhance the diagnostic accuracy of machine learning systems. However, effectively extracting and utilizing HOIs remains a significant challenge. In this work, we propose MvHo-IB, a novel multi-view learning framework that integrates both pairwise interactions and HOIs for diagnostic decision-making, while automatically compressing task-irrelevant redundant information. MvHo-IB introduces several key innovations: (1) a principled method that combines O-information from information theory with a matrix-based Renyi alpha-order entropy estimator to quantify and extract HOIs, (2) a purpose-built Brain3DCNN encoder to effectively utilize these interactions, and (3) a new multi-view learning information bottleneck objective to enhance representation learning. Experiments on three benchmark fMRI datasets demonstrate that MvHo-IB achieves state-of-the-art performance, significantly outperforming previous methods, including recent hypergraph-based techniques. The implementation of MvHo-IB is available at https://github.com/zky04/MvHo-IB.","short_abstract":"Recent evidence suggests that modeling higher-order interactions (HOIs) in functional magnetic resonance imaging (fMRI) data can enhance the diagnostic accuracy of machine learning systems. However, effectively extracting and utilizing HOIs remains a significant challenge. In this work, we propose MvHo-IB, a novel mult...","url_abs":"https://arxiv.org/abs/2507.02847","url_pdf":"https://arxiv.org/pdf/2507.02847v1","authors":"[\"Kunyu Zhang\",\"Qiang Li\",\"Shujian Yu\"]","published":"2025-07-03T17:54:03Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":612434,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2898880,"paper_url":"https://arxiv.org/abs/2507.02847","paper_title":"MvHo-IB: Multi-View Higher-Order Information Bottleneck for Brain Disorder Diagnosis","repo_url":"https://github.com/zky04/MvHo-IB","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}