PFedDST: Personalized Federated Learning with Decentralized Selection Training
This work addresses efficiency and personalization issues in federated learning for decentralized systems, representing an incremental improvement over existing methods.
The paper tackles challenges in federated learning, such as non-IID data and communication bottlenecks, by introducing PFedDST, a framework that uses decentralized peer selection to enhance model accuracy and accelerate convergence, outperforming state-of-the-art methods in handling data heterogeneity.
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.