Agnostic Federated Learning

Mehryar Mohri, Gary Sivek, Ananda Theertha Suresh

2019 · arXiv (Cornell University) · 589 citations

A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We argue that, with the existing training and inference, federated models can be biased towards different clients. Instead, we propose a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions. We further show that this framework naturally yields a notion of fairness. We present data-dependent Rademacher complexi…

Read the paper →

Explore this paper's citation graph on Constellation.