Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective

Federated learning (FL) becomes popular and has shown great potentials in training large-scale machine learning (ML) models without exposing the owners’ raw data. In FL, the data owners can train ML models based on their local data and only send the model updates rather than raw data to the model owner for aggregation. To improve learning performance in terms of model accuracy and training completion time, it is essential to recruit sufficient participants. Meanwhile, the data owners are rational and may be unwilling to participate in the collaborative learning process due to the resource consumption. To address the issues, there have been various works recently proposed to motivate the data owners to contribute their resources. In this paper, we provide a comprehensive review for the economic and game theoretic approaches proposed in the literature to design various schemes for incentivizing data owners to participate in FL training process. In particular, we first present the fundamentals and background of FL, economic theories commonly used in incentive mechanism design. Then, we review applications of game theory and economic approaches applied for incentive mechanisms design of FL. Finally, we highlight some open issues and future research directions concerning incentive mechanism design of FL.

I. Introduction

In the past few years, we have witnessed the rapid development of machine learning (ML) in the field of artificial intelligence (AI) applications, such as computer vision, automatic speech recognition, natural language processing and recommendation system [1]–[3]. The success of these machine learning technologies, especially deep learning (DL), builds on a large volume of data (i.e., big data). With the advent of the Internet of Things (IoT), massive data is collected by Internet connected smart devices with limited resources (e.g., smartphones, sensors, etc.). In most traditional ML technologies, the local data collected by smart devices need to be transmitted and processed at a cloud or data center to train effective inference models. However, this causes excessive computation and storage costs, and the smart devices also suffer from serious privacy leakage risk [4].