Proceedings

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

Hua Huang, Fanhua Shang, Yuanyuan Liu, Hongying Liu

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 2556-2562.

https://doi.org/10.24963/ijcai.2021/352

Keywords

  • Machine Learning: Deep Learning
  • Data Mining: Federated Learning

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.

Hua Huang, Fanhua Shang, Yuanyuan Liu, and Hongying Liu. 2021. Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 2556–2562. https://doi.org/10.24963/ijcai.2021/352
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards