HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients

By Enmao Diao, Jie Ding, Vahid Tarokh. International Conference on Learning Representations, 2020

749 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/f9b3ed20d6da7dfbfbd8a58e2bde173e5e9c768c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bo Du
2. Mang Ye
3. Lichao Sun
4. Pong Chi Yuen
5. Dacheng Tao
6. Philip S. Yu
7. Gillian Dobbie
8. Hongsheng Hu

Citations in the corpus

• Membership Inference Attacks on Machine Learning: A Survey (2021, background): “On the contrary, heterogeneous federated learning schemes such as FedMD [109] and HeteroFL [39] have recently been proposed to handle the system heterogeneity [111] without requiring local models to share the same architecture.”
• Heterogeneous Federated Learning: State-of-the-art and Research Challenges (2023, background): “[40] HeteroFL allocates local models of different sizes according to the computational and communication capabilities of each client.”