摘要
With the rapid development of the Internet of Things (IoT), the need to expand the amount of data through data-sharing to improve the model performance of edge devices has become increasingly compelling. To effectively protect data privacy while leveraging data across silos, federated learning has emerged. However, in the real world applications, federated learning inevitably faeces both data and model heterogeneity challenges. To address the heterogeneity issues in federated networks, in this work, we seek to jointly learn a global feature representation that is robust across clients and potentially also generalizable to new clients. More specifically, we propose a personalized Federated optimization framework with Meta Critic (FedMC) that efficiently captures robust and generalizable domain-invariant knowledge across clients. Extensive experiments on four public datasets show that the proposed FedMC outperforms the competing state-of-the-art methods in heterogeneous federated learning settings. We have also performed detailed ablation analysis on the importance of different components of the proposed model.
学科与关键词
- Personalized Federated Learning on Non-IID Data via Group-based Meta-learningYang, Lei; Huang, Jiaming; Lin, Wanyu*; Cao, JiannongACM Transactions on Knowledge Discovery from Data, 2023, 17(4).被引 13
- Efficient Federated Learning Using Layer-Wise Regulation and Momentum Aggregation*Zhang, Fan; Fang, Zekuan; Li, Yiming; Chen, Mingsong*JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2022, 31(18): 2250314.
- DM-PFL: Hitchhiking Generic Federated Learning for Efficient Shift-Robust PersonalizationZhang, Wenhao*; Zhou, Zimu; Wang, Yansheng; Tong, Yongxin29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Long Beach, CA, 2023-08-06 To 2023-08-10.
