← Search

Karan Singhal

2 accepted papers

2022

What Do We Mean by Generalization in Federated Learning?

ICLR 2022poster

Federated learning data is drawn from a distribution of distributions: clients are drawn from a meta-distribution, and their data are drawn from local data distributions. Generalization studies in federated learning should separate performance gaps from unseen client data (out-of-sample gap) from pe…

2021

Federated Reconstruction: Partially Local Federated Learning

NeurIPS 2021poster

Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity. Approaches that require clients to communicate all model parameters can be undesirable due to privacy and commu…