PFedDST: Personalized Federated Learning with Decentralized Selection Training

TL;DR

PFedDST introduces a decentralized peer selection mechanism in federated learning that improves personalization, accelerates convergence, and handles data heterogeneity more effectively than existing methods.

Contribution

It proposes a novel decentralized peer selection strategy based on communication scores to enhance federated learning personalization and efficiency.

Findings

Improves model accuracy over state-of-the-art methods.

Accelerates training convergence.

Effectively handles non-IID data distributions.

Abstract

Distributed Learning (DL) enables the training of machine learning models across multiple devices, yet it faces challenges like non-IID data distributions and device capability disparities, which can impede training efficiency. Communication bottlenecks further complicate traditional Federated Learning (FL) setups. To mitigate these issues, we introduce the Personalized Federated Learning with Decentralized Selection Training (PFedDST) framework. PFedDST enhances model training by allowing devices to strategically evaluate and select peers based on a comprehensive communication score. This score integrates loss, task similarity, and selection frequency, ensuring optimal peer connections. This selection strategy is tailored to increase local personalization and promote beneficial peer collaborations to strengthen the stability and efficiency of the training process. Our experiments demonstrate that PFedDST not only enhances model accuracy but also accelerates convergence. This approach outperforms state-of-the-art methods in handling data heterogeneity, delivering both faster and more effective training in diverse and decentralized systems.