Intelligent Agents for Auction-based Federated Learning: A Survey

arXiv:2404.13244v1 Announce Type: new
Abstract: Auction-based federated learning (AFL) is an important emerging category of FL incentive mechanism design, due to its ability to fairly and efficiently motivate high-quality data owners to join data consumers' (i.e., servers') FL training tasks. To enhance the efficiency in AFL decision support for stakeholders (i.e., data consumers, data owners, and the auctioneer), intelligent agent-based techniques have emerged. However, due to the highly interdisciplinary nature of this field and the lack of a comprehensive survey …

abstract agents arxiv consumers cs.gt cs.lg data decision decision support design efficiency federated learning intelligent join quality quality data servers stakeholders support survey tasks training type