Agent-oriented Joint Decision Support for Data Owners in Auction-based Federated Learning
It addresses a specific gap in federated learning for data owners, enabling them to manage multiple tasks simultaneously, though it is incremental in extending existing auction-based methods.
The paper tackles the lack of decision support for data owners in auction-based federated learning by proposing PAS-AFL, a joint pricing, acceptance, and sub-delegation approach that increases data owner utility by 28.77% and improves model accuracy by 2.64% on average compared to baselines.
Auction-based Federated Learning (AFL) has attracted extensive research interest due to its ability to motivate data owners (DOs) to join FL through economic means. While many existing AFL methods focus on providing decision support to model users (MUs) and the AFL auctioneer, decision support for data owners remains open. To bridge this gap, we propose a first-of-its-kind agent-oriented joint Pricing, Acceptance and Sub-delegation decision support approach for data owners in AFL (PAS-AFL). By considering a DO's current reputation, pending FL tasks, willingness to train FL models, and its trust relationships with other DOs, it provides a systematic approach for a DO to make joint decisions on AFL bid acceptance, task sub-delegation and pricing based on Lyapunov optimization to maximize its utility. It is the first to enable each DO to take on multiple FL tasks simultaneously to earn higher income for DOs and enhance the throughput of FL tasks in the AFL ecosystem. Extensive experiments based on six benchmarking datasets demonstrate significant advantages of PAS-AFL compared to six alternative strategies, beating the best baseline by 28.77% and 2.64% on average in terms of utility and test accuracy of the resulting FL models, respectively.