Incentive Mechanism Design for Semi-Asynchronous Federated Learning Based on Contract Theory: A Learning Approach

Yuan Yao, Gang Li, Hongbin Chen, Hongming Chen

Abstract: Semi-asynchronous federated learning (SAFL) leverages the benefits of synchronous and asynchronous updates, effectively addressing the straggling effect caused by heterogeneity among clients. However, most research focuses on synchronous FL, overlooking the incentive mechanisms crucial for active participation in SAFL. Moreover, client-specific private information, including data quality, computational resources, and privacy preferences is multidimensional and inaccessible to the server, yet essential for effective decision-making. To address these challenges, we propose a novel SAFL framework incorporating a learning-based contract with the consideration of multidimensional private information. Specifically, we integrate model staleness and data quality into the aggregated weight design in the proposed SAFL. Then, we formulate a server utility maximization problem to optimize local iterations and reward allocation for different client types, ensuring theoretical guarantees of convergence, individual rationality (IR), and incentive compatibility (IC). Extensive simulations on real-world datasets demonstrate that our approach significantly enhances global accuracy and convergence speed compared to existing works on aggregation and contract design methods.

External IDs:dblp:journals/iotj/YaoLCC25