A federated learning incentive mechanism in a non-monopoly market

Abstract

Federated learning, a privacy-preserving collaborative machine learning paradigm, has led to the proposal of various incentive mechanisms to encourage active participation of data owners. However, most of the existing mechanisms focused on the monopsony market scenario, where only one server-side entity (buyer) is involved. In real-world scenarios, multiple server parties may express simultaneous interest in the data of a client (seller), leading to a non-monopoly market. This paper aims to bridge this gap by introducing the concept of incentivizing federated learning in a non-monopoly market and presents a non-monopoly federated learning incentive mechanism, coined as NmFLI. NmFLI employs a double-auction mechanism to implement federated learning incentives and utilizes the Vickery–Clarke–Groves (VCG) mechanism to ensure client trustworthiness. Additionally, NmFLI devises a method for measuring data quality by calculating the value of clients based on their historical performance, which effectively balances accuracy and computational complexity. We demonstrate that NmFLI possesses properties such as individual rationality and strategy-proofness. Experimental results indicate that NmFLI can effectively incentivize federated learning and achieve higher accuracy than baseline models across various scenarios. For example, when the objectives of various tasks overlap, NmFLI outperforms the best baseline by 3.09% with imbalanced client data while maintaining the same data size. Moreover, NmFLI surpasses the best baseline by 6.12% with different amounts of client data.