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

Abstract

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.

Decentral and Incentivized Federated Learning Frameworks: A Systematic Literature Review

“…We have identified several survey papers in the context of either mechanism design and FL [22], [23], [25] or blockchain and FL [21], [23], [24]. TABLE 1 shows the comparison of the related survey papers and our own.…”

“…The other related survey papers focus on incentive mechanisms for FL [22], [23], [24], [25]. Zhan et al survey the incentive mechanism design dedicated to FL [22].…”

“…number of publishers and workers), evaluation datasets as well as advantages and disadvantages of the mechanisms and security considerations. Tu et al [25] provide a comprehensive review for economic and game theoretic approaches to incentivize data owners to participate in FL. In particular, they cluster applications of Stackelberg games, non-cooperative games, sealed-bid auction models, reverse action models as well as contract and matching theory for incentive MD in FL.…”

Maximizing Global Model Appeal in Federated Learning

“…As surveyed in [13], previous works investigating client incentives in FL have typically done so from a game-theoretic perspective and for toy problems such as mean estimation. In contrast, our work is generally applicable to non-convex objectives, and considers a server that seeks to train a single global model that will be preferred by the maximum number of clients, thus incentivizing them to participate in FL.…”

Models of fairness in federated learning

“…Federated learning is a new and rapidly growing field ( [11,8]) that combined learned parameters from multiple federating agents in order to train models with lower expected error. It has also been the subject of game theoretical analysis, such as in [2,7,6,3,4], and in the summary paper [18].…”