Intelligent Agents for Auction-based Federated Learning: A Survey

TL;DR

This survey reviews the emerging field of intelligent agent-based auction mechanisms in federated learning, highlighting their roles, challenges, and future research directions to improve stakeholder decision support.

Contribution

It provides the first comprehensive survey and a multi-tiered taxonomy of intelligent agents in auction-based federated learning, addressing a significant knowledge gap.

Findings

Organized existing IA-AFL works by stakeholders, mechanisms, and goals.

Identified limitations and challenges in current IA-AFL approaches.

Discussed evaluation metrics and future research directions.

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 providing an accessible perspective, it is a challenge for researchers to enter and contribute to this field. This paper bridges this important gap by providing a first-of-its-kind survey on the Intelligent Agents for AFL (IA-AFL) literature. We propose a unique multi-tiered taxonomy that organises existing IA-AFL works according to 1) the stakeholders served, 2) the auction mechanism adopted, and 3) the goals of the agents, to provide readers with a multi-perspective view into this field. In addition, we analyse the limitations of existing approaches, summarise the commonly adopted performance evaluation metrics, and discuss promising future directions leading towards effective and efficient stakeholder-oriented decision support in IA-AFL ecosystems.