HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
This addresses the challenge of federated learning for clients with diverse capabilities, such as mobile and IoT devices, by enabling adaptive subnetwork distribution, representing a novel method for a known bottleneck.
The paper tackles the problem of federated learning with heterogeneous clients by proposing HeteroFL, a framework that allows training local models with varying complexities to produce a single global model, demonstrating efficiency gains in computation and communication.
Federated Learning (FL) is a method of training machine learning models on private data distributed over a large number of possibly heterogeneous clients such as mobile phones and IoT devices. In this work, we propose a new federated learning framework named HeteroFL to address heterogeneous clients equipped with very different computation and communication capabilities. Our solution can enable the training of heterogeneous local models with varying computation complexities and still produce a single global inference model. For the first time, our method challenges the underlying assumption of existing work that local models have to share the same architecture as the global model. We demonstrate several strategies to enhance FL training and conduct extensive empirical evaluations, including five computation complexity levels of three model architecture on three datasets. We show that adaptively distributing subnetworks according to clients' capabilities is both computation and communication efficient.