HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients

Enmao Diao, Jie Ding, Vahid Tarokh

Keywords: Federated Learning, Internet of Things, Heterogeneity

Abstract: 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.

One-sentence Summary: In this work, we propose a new federated learning framework named HeteroFL to train heterogeneous local models with varying computation complexities.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ dem123456789/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients](https://github.com/dem123456789/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients) + [ 2 community implementations](https://paperswithcode.com/paper/?openreview=TNkPBBYFkXg)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [MNIST](https://paperswithcode.com/dataset/mnist), [WikiText-2](https://paperswithcode.com/dataset/wikitext-2)