AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems

Abstract

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.

This paper has been accepted by DAC2024

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Ensemble Distillation for Robust Model Fusion in Federated Learning
• Unifying Count-Based Exploration and Intrinsic Motivation
• HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
• GitFL: Adaptive Asynchronous Federated Learning using Version Control
• FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things

Cited by in corpus (2)

• FedCross: Towards Accurate Federated Learning via Multi-Model Cross-Aggregation
• Gradients as an Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing