A VCG-based Fair Incentive Mechanism for Federated Learning

Federated learning (FL) has shown great potential for addressing the challenge of isolated data islands while preserving data privacy. It allows artificial intelligence (AI) models to be trained on locally stored data in a distributed manner. In order to build an ecosystem for FL to operate in a sustainable manner, it has to be economically attractive to data owners. This gives rise to the problem of FL incentive mechanism design, which aims to find the optimal organizational and payment structure for the federation in order to achieve a series of economic objectives. In this paper, we present a VCG-based FL incentive mechanism, named FVCG, specifically designed for incentivizing data owners to contribute all their data and truthfully report their costs in FL settings. It maximizes the social surplus and minimizes unfairness of the federation. We provide an implementation of FVCG with neural networks and theoretic proofs on its performance bounds. Extensive numerical experiment results demonstrated the effectiveness and economic reasonableness of FVCG.

[1]  Guan Wang,et al.  Interpret Federated Learning with Shapley Values , 2019, ArXiv.

[2]  Qiang Yang,et al.  Federated Machine Learning , 2019, ACM Trans. Intell. Syst. Technol..

[3]  Peter Richtárik,et al.  Federated Learning: Strategies for Improving Communication Efficiency , 2016, ArXiv.

[4]  Peter Richtárik,et al.  Federated Optimization: Distributed Machine Learning for On-Device Intelligence , 2016, ArXiv.

[5]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[6]  Tomasz P. Michalak,et al.  Coalition structure generation: A survey , 2015, Artif. Intell..

[7]  Ariel D. Procaccia,et al.  Algorithms for strategyproof classification , 2012, Artif. Intell..

[8]  C. Efthimiou.  Introduction to Functional Equations: Theory and Problem-solving Strategies for Mathematical Competitions and Beyond , 2011 .

[9]  Alaeddin Malek,et al.  Solving initial-boundary value problems for systems of partial differential equations using neural networks and optimization techniques , 2009, J. Frankl. Inst..

[10]  P. Kannappan.  Functional Equations and Inequalities with Applications , 2009 .

[11]  Attila Gilányi,et al.  An Introduction to the Theory of Functional Equations and Inequalities , 2008 .

[12]  Ariel D. Procaccia,et al.  Incentive compatible regression learning , 2008, SODA '08.

[13]  John C. Harsanyi,et al.  Games with Incomplete Information Played by "Bayesian" Players, I-III: Part I. The Basic Model& , 2004, Manag. Sci..

[14]  Noam Nisan,et al.  Computationally feasible VCG mechanisms , 2000, EC '00.

[15]  Andrew W. Moore,et al.  Gradient descent approaches to neural-net-based solutions of the Hamilton-Jacobi-Bellman equation , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[16]  David N. Figlio.  Functional form and the estimated effects of school resources , 1999 .

[17]  Joseph Sill,et al.  Monotonic Networks , 1997, NIPS.

[18]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[19]  R. Halvorsen,et al.  Choice of functional form for hedonic price equations , 1981 .

[20]  R. Carter Hill,et al.  Recreation Demand Equations: Functional Form and Consumer Surplus , 1980 .

[21]  L. Hurwicz.  Studies in Resource Allocation Processes: Optimality and informational efficiency in resource allocation processes , 1977 .

[22]  Walter Diewert,et al.  Functional Forms for Revenue and Factor Requirements Functions , 1974 .

[23]  E. H. Clarke.  Multipart pricing of public goods , 1971 .

[24]  William Vickrey,et al.  Counterspeculation, Auctions, And Competitive Sealed Tenders , 1961 .

[25]  L. Hurwicz.  On informationally decentralized systems , 1977 .