Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g., computing capacity, memory size) of devices and uncertain operating environments. To address these issues, this paper introduces an effective FL approach named AdaptiveFL based on a novel fine-grained width-wise model pruning strategy, which can generate various heterogeneous local models for heterogeneous AIoT devices. By using our proposed reinforcement learning-based device selection mechanism, AdaptiveFL can adaptively dispatch suitable heterogeneous models to corresponding AIoT devices on the fly based on their available resources for local training. Experimental results show that, compared to state-of-the-art methods, AdaptiveFL can achieve up to 16.83% inference improvements for both IID and non-IID scenarios.
@article{arxiv.2311.13166,
title = {AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems},
author = {Chentao Jia and Ming Hu and Zekai Chen and Yanxin Yang and Xiaofei Xie and Yang Liu and Mingsong Chen},
journal= {arXiv preprint arXiv:2311.13166},
year = {2024}
}