부산대학교 도서관

As an emerging privacy-preserving collaborative machine learning paradigm, the success of federated learning (FL) relies heavily on effectively motivating data owners (a.k.a. FL clients) to contribute high-quality local data and computational resources towards FL model training. Rewarding clients with incentives has been identified as a useful approach towards this goal. It is often implemented in conjunction with auction-based federated learning (AFL). Nevertheless, this approach introduces new challenges for FL servers (a.k.a. federations) as they must work within a limited budget and make trade-off decisions between hiring FL clients, saving costs and achieving target model performance. The dynamic nature of AFL further complicates this problem as federations need to consider potential competition from other federations. To address this challenge, we propose the Reputation-aware Opportunistic Budget Optimization approach for Auction-based Federated Learning (ROBO-AFL). Based on Lyapunov optimization, it helps federations maximize their utility by determining the time-averaged optimal allocation of budget for the hiring FL clients. Extensive experimental evaluation based on real-world data demonstrates that compared to four state-of-the-art approaches, ROBO-AFL achieves the most advantageous trade-off between fairness, cost-effectiveness and utility with 1.80% higher utility with 62.85% lower cost than the best-performing baseline, while maintaining a comparably high level of fairness. To the best of our knowledge, ROBO-AFL is the first decision support approach designed to help federations optimize their budget usage in competitive and open AFL markets.