ClusterFL: A Clustering-based Federated Learning System for Human Activity Recognition
Publication in refereed journal

Times Cited
Altmetrics Information

Other information
AbstractFederated Learning (FL) has recently received significant interests thanks to its capability of protecting data privacy. However, existing FL paradigms yield unsatisfactory performance for a wide class of human activity recognition (HAR) applications since they are oblivious to the intrinsic relationship between data of different users. We propose ClusterFL, a clustering-based federated learning system that can provide high model accuracy and low communication overhead for HAR applications. ClusterFL features a novel clustered multi-task federated learning framework that minimizes the empirical training loss of multiple learned models while automatically capturing the intrinsic clustering relationship among the nodes. We theoretically prove the convergence of proposed FL framework for non-convex and strongly convex models, and provide the guidance on selection of hyper-parameters for achieving such convergence. Based on the learned cluster relationship, ClusterFL can efficiently drop the nodes that converge slower or have little correlations with others in each cluster, significantly speeding up the convergence while maintaining the accuracy performance. We evaluate the performance of ClusterFL on an NVIDIA edge testbed using four new HAR datasets collected from 145 users. The results show that, ClusterFL outperforms several state-of-the-art FL paradigms in terms of overall accuracy, and can save more than 50% communication overhead.
Acceptance Date14/07/2022
All Author(s) ListOuyang Xiaomin, Xie Zhiyuan, Zhou Jiayu, Xing Guoliang, Huang Jianwei
Journal nameACM Transactions on Sensor Networks
Volume Number19
Issue Number1
PublisherAssociation for Computing Machinery
Article number17
LanguagesEnglish-United States

Last updated on 2024-09-04 at 00:38