FedSoft: Soft Clustered Federated Learning with Proximal Local Updating
FedSoft: Soft Clustered Federated Learning with Proximal Local Updating
复制标题
DOI：
10.1609/aaai.v36i7.20785
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Yichen Ruan;Carlee Joe-Wong
中科院分区：
文献类型：
--
作者：
Yichen Ruan;Carlee Joe-Wong
传统上，集群联合学习将具有相同数据分布的客户端分组到集群中，以便每个客户端与一个数据分布唯一关联，并帮助训练该分布的模型。我们将这种硬关联假设放宽到软聚类联邦学习，它允许每个本地数据集遵循多个源分布的混合。我们提出了FedSoft，它在这种环境中训练本地个性化模型和高质量的集群模型。FedSoft通过使用邻近更新来限制客户端的工作负载，要求在每个通信回合中只完成来自客户端子集的一个优化任务。我们通过分析和经验表明，FedSoft有效地利用了源分布之间的相似性来学习表现良好的个性化和集群模型。
Traditionally, clustered federated learning groups clients with the same data distribution into a cluster, so that every client is uniquely associated with one data distribution and helps train a model for this distribution. We relax this hard association assumption to soft clustered federated learning, which allows every local dataset to follow a mixture of multiple source distributions. We propose FedSoft, which trains both locally personalized models and high-quality cluster models in this setting. FedSoft limits client workload by using proximal updates to require the completion of only one optimization task from a subset of clients in every communication round. We show, analytically and empirically, that FedSoft effectively exploits similarities between the source distributions to learn personalized and cluster models that perform well.