{"ID":2850263,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.24776","arxiv_id":"2510.24776","title":"CFL-SparseMed: Communication-Efficient Federated Learning for Medical Imaging with Top-k Sparse Updates","abstract":"Secure and reliable medical image classification is crucial for effective patient treatment, but centralized models face challenges due to data and privacy concerns. Federated Learning (FL) enables privacy-preserving collaborations but struggles with heterogeneous, non-IID data and high communication costs, especially in large networks. We propose \\textbf{CFL-SparseMed}, an FL approach that uses Top-k Sparsification to reduce communication overhead by transmitting only the top k gradients. This unified solution effectively addresses data heterogeneity while maintaining model accuracy. It enhances FL efficiency, preserves privacy, and improves diagnostic accuracy and patient care in non-IID medical imaging settings. The reproducibility source code is available on \\href{https://github.com/Aniket2241/APK_contruct}{Github}.","short_abstract":"Secure and reliable medical image classification is crucial for effective patient treatment, but centralized models face challenges due to data and privacy concerns. Federated Learning (FL) enables privacy-preserving collaborations but struggles with heterogeneous, non-IID data and high communication costs, especially...","url_abs":"https://arxiv.org/abs/2510.24776","url_pdf":"https://arxiv.org/pdf/2510.24776v1","authors":"[\"Gousia Habib\",\"Aniket Bhardwaj\",\"Ritvik Sharma\",\"Shoeib Amin Banday\",\"Ishfaq Ahmad Malik\"]","published":"2025-10-25T09:13:06Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\",\"cs.DC\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":607782,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2850263,"paper_url":"https://arxiv.org/abs/2510.24776","paper_title":"CFL-SparseMed: Communication-Efficient Federated Learning for Medical Imaging with Top-k Sparse Updates","repo_url":"https://github.com/Aniket2241/APK_contruct","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}