Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. In practical FL applications, local data from each data silo reflect local usage patterns. Therefore, there exists heterogeneity of data distributions among data owners (a.k.a. FL clients). If not handled properly, this can lead to model performance degradation. This challenge has inspired the research field of heterogeneous federated learning, which currently remains open. In this paper, we propose a data heterogeneity-robust FL approach, FedGSP, to address this challenge by leveraging on a novel concept of dynamic Sequential-to-Parallel (STP) collaborative training. FedGSP assigns FL clients to homogeneous groups to minimize the overall distribution divergence among groups, and increases the degree of parallelism by reassigning more groups in each round. It is also incorporated with a novel Inter-Cluster Grouping (ICG) algorithm to assist in group assignment, which uses the centroid equivalence theorem to simplify the NP-hard grouping problem to make it solvable. Extensive experiments have been conducted on the non-i.i.d. FEMNIST dataset. The results show that FedGSP improves the accuracy by 3.7% on average compared with seven state-of-the-art approaches, and reduces the training time and communication overhead by more than 90%.
翻译:联邦学习(FL)是一个快速增长的隐私保护协作机器学习模式。在实际的 FL 应用中,每个数据库的本地数据反映当地使用模式。因此,数据所有者(a.k.a.FL客户端)之间数据分布差异不一,如果处理不当,这可能导致模式性性能退化。这一挑战激励了目前仍然开放的多种联邦学习的研究领域。在本文中,我们提议采用数据差异性-机器人FedGSP方法,通过利用动态序列到Parallel(STP)合作培训的新概念来应对这一挑战。FedGSP将FL客户指派给同质群体,以尽量减少各群体之间的总体分布差异,并通过在每轮中重新指派更多群体来增加平行程度。这个挑战还被纳入了一个新的跨集团(ICG)算法,以协助群体任务分配,该算法使用丙醇等同理论来简化NP-硬组问题的新概念,使其可以溶解到Parall(STP)合作培训模式。FGP-M- sloaralalalalalalalalalalalalalalalalalalalizationalizations by the droadal-dalalaltialti laveal lavedaldaldalti lavedaldaldaldaldaldaldaldaldddddddddddddddddddddalddddddddaldddddal 7MIstalddddaldal-daldaldaldaldddaldaldalddddddddddddddaldddddddddaldaldaldaldaldaldaldaldaldaldaldalddaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldal