Strategic Client Selection to Address Non-IIDness in HAPS-enabled FL Networks

2024-01-10

arXiv.org

AI Summary

To address the non-independent and identically distributed (non-IID) data challenge in federated learning (FL) over High-Altitude Platform Station (HAPS)-enabled non-terrestrial networks (NTNs), this paper proposes a weighted attribute-driven dynamic client selection mechanism. The method innovatively integrates four dimensions—historical traffic volume, channel state information, device computational capability, and historical model contribution—into a multi-attribute weighted scoring model to adaptively select clients with more balanced and representative data distributions. It operates under practical communication and computation resource constraints. Experimental results on large-scale non-IID scenarios demonstrate that the proposed approach achieves an 8.2% accuracy improvement and reduces convergence rounds by 37% compared to baseline methods, while also lowering training loss and accelerating global model convergence. These results validate its effectiveness and practicality in integrated space-air-ground FL systems.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Multiagent Systems: Mechanism Design

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 evaluation methodologies and metrics

Abstract

The deployment of federated learning (FL) in non-terrestrial networks (NTN) that are supported by high-altitude platform stations (HAPS) offers numerous advantages. Due to its large footprint, it facilitates interaction with a large number of line-of-sight (LoS) ground clients, each possessing diverse datasets along with distinct communication and computational capabilities. The presence of many clients enhances the accuracy of the FL model and speeds up convergence. However, the variety of datasets among these clients poses a significant challenge, as it leads to pervasive non-independent and identically distributed (non-IID) data. The data non-IIDness results in markedly reduced training accuracy and slower convergence rates. To address this issue, we propose a novel weighted attribute-based client selection strategy that leverages multiple user-specific attributes, including historical traffic patterns, instantaneous channel conditions, computational capabilities, and previous-round learning performance. By combining these attributes into a composite score for each user at every FL round and selecting users with higher scores as FL clients, the framework ensures more uniform and representative data distributions, effectively mitigating the adverse effects of non-IID data. Simulation results corroborate the effectiveness of the proposed client selection strategy in enhancing FL model accuracy and convergence rate, as well as reducing training loss, by effectively addressing the critical challenge of data non-IIDness in large-scale FL system implementations.

Problem

• Addressing non-IID data in HAPS-enabled FL networks
• Improving FL model accuracy and convergence rate
• Selecting clients based on weighted attribute strategy

Innovation

• Weighted attribute-based client selection strategy
• Leverages user-specific attributes for scoring
• Ensures uniform data distribution in FL