Long-Term Client Selection for Federated Learning with Non-IID Data: A Truthful Auction Approach

2025-08-07

AI Summary

In vehicular edge federated learning, persistent client selection under non-IID data exacerbates resource waste, information asymmetry (due to intermittent connectivity and limited on-board computation), and strategic misreporting of capabilities. Method: We propose a long-term quality-aware client selection mechanism grounded in a trust-enabled auction framework. It jointly models dynamic data quality evolution, energy cost, and a deposit-based truthful auction to ensure incentive compatibility and individual rationality. Contribution/Results: Our approach unifies reputation accumulation, truthfulness guarantees, and resource efficiency optimization within a longitudinal selection paradigm. Extensive experiments across multiple vehicular datasets demonstrate significant improvements: accelerated model convergence and higher accuracy, effective mitigation of non-IID effects, and gains of 18.7% in social welfare and 23.4% in training resource utilization over baselines.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Learning to Search
• Machine Learning: Life-Long and Continual Learning

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Federated learning (FL) provides a decentralized framework that enables universal model training through collaborative efforts on mobile nodes, such as smart vehicles in the Internet of Vehicles (IoV). Each smart vehicle acts as a mobile client, contributing to the process without uploading local data. This method leverages non-independent and identically distributed (non-IID) training data from different vehicles, influenced by various driving patterns and environmental conditions, which can significantly impact model convergence and accuracy. Although client selection can be a feasible solution for non-IID issues, it faces challenges related to selection metrics. Traditional metrics evaluate client data quality independently per round and require client selection after all clients complete local training, leading to resource wastage from unused training results. In the IoV context, where vehicles have limited connectivity and computational resources, information asymmetry in client selection risks clients submitting false information, potentially making the selection ineffective. To tackle these challenges, we propose a novel Long-term Client-Selection Federated Learning based on Truthful Auction (LCSFLA). This scheme maximizes social welfare with consideration of long-term data quality using a new assessment mechanism and energy costs, and the advised auction mechanism with a deposit requirement incentivizes client participation and ensures information truthfulness. We theoretically prove the incentive compatibility and individual rationality of the advised incentive mechanism. Experimental results on various datasets, including those from IoV scenarios, demonstrate its effectiveness in mitigating performance degradation caused by non-IID data.

Problem

• Addressing non-IID data impact on federated learning convergence
• Optimizing long-term client selection with truthful auction mechanisms
• Reducing resource wastage in vehicular federated learning systems

Innovation

• Long-term client selection using truthful auction
• Novel assessment mechanism for data quality
• Deposit requirement ensures information truthfulness