FedCCA: Client-Centric Adaptation against Data Heterogeneity in Federated Learning on IoT Devices

2026-01-25

AI Summary

This work proposes a client-centric adaptive federated learning framework to address the performance degradation and slow convergence caused by data heterogeneity in Internet of Things (IoT) devices. The approach introduces client-specific encoders and a selective adaptation mechanism, complemented by dynamic client selection and an attention-driven global aggregation strategy. This design enables personalized model training while preserving data privacy. In contrast to conventional fixed aggregation paradigms, the proposed method substantially mitigates the adverse effects of data heterogeneity. Experimental results across multiple benchmark datasets demonstrate that the framework consistently outperforms existing approaches, achieving both enhanced model accuracy and accelerated convergence.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

With the rapid development of the Internet of Things (IoT), AI model training on private data such as human sensing data is highly desired. Federated learning (FL) has emerged as a privacy-preserving distributed training framework for this purpuse. However, the data heterogeneity issue among IoT devices can significantly degrade the model performance and convergence speed in FL. Existing approaches limit in fixed client selection and aggregation on cloud server, making the privacy-preserving extraction of client-specific information during local training challenging. To this end, we propose Client-Centric Adaptation federated learning (FedCCA), an algorithm that optimally utilizes client-specific knowledge to learn a unique model for each client through selective adaptation, aiming to alleviate the influence of data heterogeneity. Specifically, FedCCA employs dynamic client selection and adaptive aggregation based on the additional client-specific encoder. To enhance multi-source knowledge transfer, we adopt an attention-based global aggregation strategy. We conducted extensive experiments on diverse datasets to assess the efficacy of FedCCA. The experimental results demonstrate that our approach exhibits a substantial performance advantage over competing baselines in addressing this specific problem.

Problem

• data heterogeneity
• federated learning
• IoT devices
• client-specific adaptation
• privacy-preserving

Innovation

• federated learning
• data heterogeneity
• client-centric adaptation
• dynamic client selection
• attention-based aggregation