FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices
This addresses the problem of high computation and communication overhead in federated learning for edge computing scenarios, but it is incremental as it builds on existing one-shot and model-heterogeneous FL methods.
The paper tackles the challenge of managing model-heterogeneous one-shot federated learning for resource-constrained edge devices by proposing FedMHO, a framework that uses deep classification models on resource-sufficient clients and lightweight generative models on constrained devices, with results showing it outperforms state-of-the-art baselines in various setups.
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.