FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices

TL;DR

FedMHO is a novel federated learning framework that enables effective one-shot, model-heterogeneous training on resource-constrained edge devices by combining deep and lightweight models with data generation and knowledge fusion techniques.

Contribution

The paper introduces FedMHO, a new framework for one-shot, model-heterogeneous federated learning tailored for resource-limited edge devices, with innovative data generation and knowledge fusion methods.

Findings

Outperforms state-of-the-art baselines in various setups.

Effectively manages model heterogeneity and resource constraints.

Mitigates knowledge-forgetting during model fusion.

Abstract

Federated Learning (FL) is increasingly adopted in edge computing scenarios, where a large number of heterogeneous clients operate under constrained or sufficient resources. The iterative training process in conventional FL introduces significant computation and communication overhead, which is unfriendly for resource-constrained edge devices. One-shot FL has emerged as a promising approach to mitigate communication overhead, and model-heterogeneous FL solves the problem of diverse computing resources across clients. However, existing methods face challenges in effectively managing model-heterogeneous one-shot FL, often leading to unsatisfactory global model performance or reliance on auxiliary datasets. To address these challenges, we propose a novel FL framework named FedMHO, which leverages deep classification models on resource-sufficient clients and lightweight generative models on resource-constrained devices. On the server side, FedMHO involves a two-stage process that includes data generation and knowledge fusion. Furthermore, we introduce FedMHO-MD and FedMHO-SD to mitigate the knowledge-forgetting problem during the knowledge fusion stage, and an unsupervised data optimization solution to improve the quality of synthetic samples. Comprehensive experiments demonstrate the effectiveness of our methods, as they outperform state-of-the-art baselines in various experimental setups.