Abstract
Federated Learning (FL) models often experience client drift caused by heterogeneous data, where the distribution of data differs across clients. To address this issue, advanced research primarily focuses on manipulating the existing gradients to achieve more consistent client models. In this paper, we present an alternative perspective on client drift and aim to mitigate it by generating improved local models. First, we analyze the generalization contribution of local training and conclude that this generalization contribution is bounded by the conditional Wasserstein distance between the data distribution of different clients. Then, we propose FedImpro, to construct similar conditional distributions for local training. Specifically, FedImpro decouples the model into high-level and low-level components, and trains the high-level portion on reconstructed feature distributions. This approach enhances the generalization contribution and reduces the dissimilarity of gradients in FL. Experimental results show that FedImpro can help FL defend against data heterogeneity and enhance the generalization performance of the model.
Original language | English |
---|---|
Title of host publication | Proceedings of the Twelfth International Conference on Learning Representations, ICLR 2024 |
Publisher | International Conference on Learning Representations |
Pages | 1-30 |
Number of pages | 30 |
Publication status | Published - May 2024 |
Event | 12th International Conference on Learning Representations, ICLR 2024 - Messe Wien Exhibition and Congress Center, Vienna, Austria Duration: 7 May 2024 → 11 May 2024 https://iclr.cc/Conferences/2024 (Conference website) https://iclr.cc/virtual/2024/calendar (Conference schedule ) https://openreview.net/group?id=ICLR.cc/2024/Conference#tab-accept-oral (Conference proceedings) |
Publication series
Name | Proceedings of the International Conference on Learning Representations, ICLR |
---|
Conference
Conference | 12th International Conference on Learning Representations, ICLR 2024 |
---|---|
Country/Territory | Austria |
City | Vienna |
Period | 7/05/24 → 11/05/24 |
Internet address |
|
Scopus Subject Areas
- Language and Linguistics
- Computer Science Applications
- Education
- Linguistics and Language