Dynamic Clustering for Personalized Federated Learning on Heterogeneous Edge Devices
By: Heting Liu , Junzhe Huang , Fang He and more
Potential Business Impact:
Groups devices for faster, accurate AI learning
Federated Learning (FL) enables edge devices to collaboratively learn a global model, but it may not perform well when clients have high data heterogeneity. In this paper, we propose a dynamic clustering algorithm for personalized federated learning system (DC-PFL) to address the problem of data heterogeneity. DC-PFL starts with all clients training a global model and gradually groups the clients into smaller clusters for model personalization based on their data similarities. To address the challenge of estimating data heterogeneity without exposing raw data, we introduce a discrepancy metric called model discrepancy, which approximates data heterogeneity solely based on the model weights received by the server. We demonstrate that model discrepancy is strongly and positively correlated with data heterogeneity and can serve as a reliable indicator of data heterogeneity. To determine when and how to change grouping structures, we propose an algorithm based on the rapid decrease period of the training loss curve. Moreover, we propose a layer-wise aggregation mechanism that aggregates the low-discrepancy layers at a lower frequency to reduce the amount of transmitted data and communication costs. We conduct extensive experiments on various datasets to evaluate our proposed algorithm, and our results show that DC-PFL significantly reduces total training time and improves model accuracy compared to baselines.
Similar Papers
CO-PFL: Contribution-Oriented Personalized Federated Learning for Heterogeneous Networks
Machine Learning (CS)
Makes AI learn better from everyone's unique data.
Not All Clients Are Equal: Personalized Federated Learning on Heterogeneous Multi-Modal Clients
Machine Learning (CS)
AI learns from everyone without sharing private data.
LCFed: An Efficient Clustered Federated Learning Framework for Heterogeneous Data
Machine Learning (CS)
Makes AI learn better from different groups of data.