Multi-Model Federated Learning with Provable Guarantees
This work addresses efficiency and scalability issues in federated learning for edge devices, though it is incremental as it builds on existing FedAvg methods.
The paper tackles the problem of training multiple independent models simultaneously in federated learning, proposing two variants of FedAvg with provable convergence guarantees and showing that multi-model FL can achieve better performance than separate training for the same computation.
Federated Learning (FL) is a variant of distributed learning where edge devices collaborate to learn a model without sharing their data with the central server or each other. We refer to the process of training multiple independent models simultaneously in a federated setting using a common pool of clients as multi-model FL. In this work, we propose two variants of the popular FedAvg algorithm for multi-model FL, with provable convergence guarantees. We further show that for the same amount of computation, multi-model FL can have better performance than training each model separately. We supplement our theoretical results with experiments in strongly convex, convex, and non-convex settings.