Toward an Automated Auction Framework for Wireless Federated Learning Services Market

TLDR

Federated learning enables model training while keeping data local, but its success depends on sufficient participation of data owners amid growing privacy concerns. This study proposes an auction‑based market model to incentivize data owners to join federated learning. We design two strategy‑proof auction mechanisms—an approximate version guaranteeing truthfulness, individual rationality, and efficiency, and an automated version employing deep reinforcement learning and graph neural networks to enhance social welfare while accounting for communication congestion. Experiments show the mechanisms effectively maximize social welfare and provide actionable insights for federated training platforms.

Abstract

In traditional machine learning, the central server first collects the data owners' private data together and then trains the model. However, people's concerns about data privacy protection are dramatically increasing. The emerging paradigm of federated learning efficiently builds machine learning models while allowing the private data to be kept at local devices. The success of federated learning requires sufficient data owners to jointly utilize their data, computing and communication resources for model training. In this article, we propose an auction-based market model for incentivizing data owners to participate in federated learning. We design two auction mechanisms for the federated learning platform to maximize the social welfare of the federated learning services market. Specifically, we first design an approximate strategy-proof mechanism which guarantees the truthfulness, individual rationality, and computational efficiency. To improve the social welfare, we develop an automated strategy-proof mechanism based on deep reinforcement learning and graph neural networks. The communication traffic congestion and the unique characteristics of federated learning are particularly considered in the proposed model. Extensive experimental results demonstrate that our proposed auction mechanisms can efficiently maximize the social welfare and provide effective insights and strategies for the platform to organize the federated training.