Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning

no code implementations • 7 Nov 2022 • Hongrui Shi, Valentin Radu, Po Yang

The heterogeneity of hardware and data is a well-known and studied problem in the community of Federated Learning (FL) as running under heterogeneous settings.

Federated Learning Knowledge Distillation

Data Selection for Efficient Model Update in Federated Learning

no code implementations • 5 Nov 2021 • Hongrui Shi, Valentin Radu

Our experiments show that only 1. 6% of the initially exchanged data can effectively transfer the characteristic of the client data to the global model in our FL approach, using split networks.

Federated Learning Transfer Learning