FedBiCross: Personalized One-Shot Federated Learning on Medical Images
FedBiCross: 医学图像上的个性化一次性联邦学习
机构 * School of Computer Science and Engineering, Northwestern Polytechnical University, China(西北工业大学计算机科学与工程学院) ; School of Science and Technology, Hong Kong Metropolitan University, Hong Kong(香港 Metropolitan 大学科学与技术学院) ; Department of Computer Science, Hong Kong Baptist University, Hong Kong(香港 Baptist 大学计算机科学系)
专题命中 医学数据与评测 :medical image(title,abstract);分类 cs.LG
AI总结 提出FedBiCross框架,通过聚类、双层跨簇优化和个性化蒸馏解决非独立同分布数据下一次性联邦学习中知识蒸馏效果差的问题,在四个医学图像数据集上优于现有方法。
Comments Accepted by BlockSys 2026. This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections