Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning

no code implementations • 31 May 2023 • M. Yashwanth, Gaurav Kumar Nayak, Arya Singh, Yogesh Simmhan, Anirban Chakraborty

In practice, there can often be substantial heterogeneity (e. g., class imbalance) across the local data distributions observed by each of these clients.

Federated Learning