Fairness-Aware Reverse Auction-Based Federated Learning

Auction-based federated learning (AFL) has garnered significant research attention recently. However, existing methods for AFL data consumers (DCs) primarily focus on improving FL model performance by recruiting data owners (DOs) with high reputations and low ask prices, disregarding fair treatment for DOs. The challenge of striking a balance between performance and fairness when recruiting DOs remains unaddressed. To tackle this issue, we propose the Fairness-aware Reverse AFL for DCs (<monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FAR-AFL</monospace>). <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FAR-AFL</monospace> leverages Lyapunov optimization to dynamically adjust selection probabilities for potential DOs, taking into account dynamic changes in participation rates and reputation. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FAR-AFL</monospace> adopts a reverse auction-based DO recruitment mechanism to determine candidate selection and pricing. By combining these components, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FAR-AFL</monospace> improves FL model accuracy while minimizing overall recruitment costs. Crucially, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FAR-AFL</monospace> ensures equitable DO treatment, providing them with fair participation opportunities. Theoretical analysis shows the computational efficiency, individual rationality, and truthfulness of <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FAR-AFL</monospace>. Extensive experimental evaluation against six alternative strategies on four benchmark datasets demonstrates that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FAR-AFL</monospace> outperforms the best alternative strategy by 1.99%, 6.60%, 1.97%, and 23.31% in terms of test accuracy, root mean square error, cost reduction, and fairness improvement, respectively.