Multi-Session Budget Optimization for Forward Auction-based Federated Learning

TL;DR

This paper introduces MultiBOS-AFL, a hierarchical reinforcement learning approach that optimizes budget pacing and bidding strategies across multiple sessions in auction-based federated learning, significantly improving utility and data acquisition.

Contribution

It presents the first budget optimization method with pacing for multi-session auction-based federated learning, addressing a previously open problem.

Findings

Achieves 12.28% higher utility than baselines

Acquires 14.52% more data within the same budget

Improves test accuracy by 1.23% over the best baseline

Abstract

Auction-based Federated Learning (AFL) has emerged as an important research field in recent years. The prevailing strategies for FL model users (MUs) assume that the entire team of the required data owners (DOs) for an FL task must be assembled before training can commence. In practice, an MU can trigger the FL training process multiple times. DOs can thus be gradually recruited over multiple FL model training sessions. Existing bidding strategies for AFL MUs are not designed to handle such scenarios. Therefore, the problem of multi-session AFL remains open. To address this problem, we propose the Multi-session Budget Optimization Strategy for forward Auction-based Federated Learning (MultiBOS-AFL). Based on hierarchical reinforcement learning, MultiBOS-AFL jointly optimizes inter-session budget pacing and intra-session bidding for AFL MUs, with the objective of maximizing the total utility. Extensive experiments on six benchmark datasets show that it significantly outperforms seven state-of-the-art approaches. On average, MultiBOS-AFL achieves 12.28% higher utility, 14.52% more data acquired through auctions for a given budget, and 1.23% higher test accuracy achieved by the resulting FL model compared to the best baseline. To the best of our knowledge, it is the first budget optimization decision support method with budget pacing capability designed for MUs in multi-session forward auction-based federated learning