Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning

7Citations
Citations of this article
14Readers
Mendeley users who have this article in their library.

Abstract

Federated Learning (FL) has become an active and promising distributed machine learning paradigm. As a result of statistical heterogeneity, recent studies clearly show that the performance of popular FL methods (e.g., FedAvg) deteriorates dramatically due to the client drift caused by local updates. This paper proposes a novel Federated Learning algorithm (called IGFL), which leverages both Individual and Group behaviors to mimic distribution, thereby improving the ability to deal with heterogeneity. Unlike existing FL methods, our IGFL can be applied to both client and server optimization. As a by-product, we propose a new attention-based federated learning in the server optimization of IGFL. To the best of our knowledge, this is the first time to incorporate attention mechanisms into federated optimization. We conduct extensive experiments and show that IGFL can significantly improve the performance of existing federated learning methods. Especially when the distributions of data among individuals are diverse, IGFL can improve the classification accuracy by about 13% compared with prior baselines.

Cite

CITATION STYLE

APA

Huang, H., Shang, F., Liu, Y., & Liu, H. (2021). Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning. In IJCAI International Joint Conference on Artificial Intelligence (pp. 2556–2562). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2021/352

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free