Exploiting Feature Heterogeneity for Improved Generalization in Federated Multi-task Learning

We prove that statistical heterogeneity in federated learning can enhance generalization performance under certain conditions.

Recommended citation: Renpu Liu, Jing Yang, and Cong Shen. (2023). "Exploiting Feature Heterogeneity for Improved Generalization in Federated Multi-task Learning." ISIT 2023.
Download Paper