arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15947cs.LGcs.DC
收藏

非IID数据的任务型联邦学习

Federated Learning with Taskonomy for Non-IID Data

Shell Global Solutions International B.V.(壳牌全球解决方案国际有限公司);Delft University of Technology (TU Delft)(代尔夫特理工大学);Myant Inc.(迈安特公司)

Hadi Jamali-Rad, Mohammad Abdizadeh, Anuj Singh

摘要:

经典的联邦学习方法在存在非IID客户端数据的情况下会导致显著的性能下降。解决这个问题的一个可能的方向是形成具有大致IID数据的客户端集群。遵循这个方向的大多数解决方案都是迭代的,并且相对较慢,在发现潜在的集群形成时也容易出现收敛问题。我们介绍了联邦学习与任务分类法(FLT),通过学习客户端之间的任务相关性来更有效地联合聚合异构数据,从而概括了这一方向。在一个一次性的过程中,服务器为客户端提供一个预先训练(和微调)的编码器,将其数据压缩成潜在的表示,并将其数据的签名传输回服务器。然后,服务器通过流形学习来学习客户端之间的任务相关性,并执行联邦平均的泛化。FLT可以灵活地处理一个通用的客户端相关性图,当没有显式的客户端集群,以及有效地将其分解成(不相交)集群的联邦学习。我们证明,FLT不仅优于现有的国家的最先进的基线在非IID的情况下,但也提供了更好的公平性在客户端。

英文摘要:

Classical federated learning approaches incur significant performance degradation in the presence of non-IID client data. A possible direction to address this issue is forming clusters of clients with roughly IID data. Most solutions following this direction are iterative and relatively slow, also prone to convergence issues in discovering underlying cluster formations. We introduce federated learning with taskonomy (FLT) that generalizes this direction by learning the task-relatedness between clients for more efficient federated aggregation of heterogeneous data. In a one-off process, the server provides the clients with a pretrained (and fine-tunable) encoder to compress their data into a latent representation, and transmit the signature of their data back to the server. The server then learns the task-relatedness among clients via manifold learning, and performs a generalization of federated averaging. FLT can flexibly handle a generic client relatedness graph, when there are no explicit clusters of clients, as well as efficiently decompose it into (disjoint) clusters for clustered federated learning. We demonstrate that FLT not only outperforms the existing state-of-the-art baselines in non-IID scenarios but also offers improved fairness across clients.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑