pFedWN: A Personalized Federated Learning Framework for D2D Wireless Networks with Heterogeneous Data

2025-01-16

AI Summary

To address the challenges of non-independent and identically distributed (non-IID) data, dynamic time-varying channels, and the absence of a central server in device-to-device (D2D) wireless networks, this paper proposes a decentralized personalized federated learning (PFL) framework. The method innovatively integrates deep channel-state embedding into the learning process and designs a channel-aware neighbor selection mechanism. It introduces, for the first time, an Expectation-Maximization (EM) algorithm to model client similarity, enabling channel-driven adaptive weight assignment. Additionally, it incorporates an Industrial-Scientific-Medical (ISM) band dynamic spectrum access strategy. Experimental results demonstrate that the proposed approach significantly improves personalized model accuracy across clients under non-IID and data-imbalanced conditions. Compared with state-of-the-art federated learning (FL) and PFL baselines, it achieves faster convergence and enhanced robustness in high-interference, low-SNR environments.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Multiagent Systems: Multiagent Learning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Traditional Federated Learning (FL) approaches often struggle with data heterogeneity across clients, leading to suboptimal model performance for individual clients. To address this issue, Personalized Federated Learning (PFL) emerges as a solution to the challenges posed by non-independent and identically distributed (non-IID) and unbalanced data across clients. Furthermore, in most existing decentralized machine learning works, a perfect communication channel is considered for model parameter transmission between clients and servers. However, decentralized PFL over wireless links introduces new challenges, such as resource allocation and interference management. To overcome these challenges, we formulate a joint optimization problem that incorporates the underlying device-to-device (D2D) wireless channel conditions into a server-free PFL approach. The proposed method, dubbed pFedWN, optimizes the learning performance for each client while accounting for the variability in D2D wireless channels. To tackle the formulated problem, we divide it into two sub-problems: PFL neighbor selection and PFL weight assignment. The PFL neighbor selection is addressed through channel-aware neighbor selection within unlicensed spectrum bands such as ISM bands. Next, to assign PFL weights, we utilize the Expectation-Maximization (EM) method to evaluate the similarity between clients' data and obtain optimal weight distribution among the chosen PFL neighbors. Empirical results show that pFedWN provides efficient and personalized learning performance with non-IID and unbalanced datasets. Furthermore, it outperforms the existing FL and PFL methods in terms of learning efficacy and robustness, particularly under dynamic and unpredictable wireless channel conditions.

Problem

• D2D Wireless Networks
• Personalized Learning
• Data Heterogeneity

Innovation

• pFedWN
• Personalized Federated Learning
• D2D Wireless Networks