From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
从坐标匹配到结构对齐:重新思考异构联邦学习中的原型对齐
机构 * State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University(虚拟现实技术与系统国家重点实验室,计算机科学与工程学院,北京航空航天大学) ; Zhongguancun Laboratory(中关村实验室) ; Center for AI Business Innovation, Department of Management Science and Systems, School of Management, University at Buffalo(人工智能商业创新中心,管理科学与系统系,布法罗大学)
AI总结 本文提出FedSAF方法,通过将对齐目标从绝对坐标转向类别间关系结构,解决了异构联邦学习中坐标对齐的局限性,提升了模型性能。
Comments 14 pages, 10 figures, 9 tables