Mechanism Design for An Incentive-aware Blockchain-enabled Federated Learning Platform
Authors:
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 395-403
Abstract
Recent technological evolution enables Artificial Intelligence (AI) model training by users’ mobile devices, which accelerates decentralized big data analysis. In particular, Federated Learning (FL) is a key enabler to realize decentralized AI model update without user’s privacy disclosure. However, since the behaviour of workers, who are assigned a training task, cannot be monitored, the state-of-the-art methods require a special hardware and/or cryptography to force the workers behave honestly, which hinders the realization. Furthermore, although blockchain-enabled FL has been proposed to give workers reward, any rigorous reward policy design has not been discussed. In this paper, to tackle these issues, we present a novel method using mechanism design, which is an economic approach to realize desired objectives under the situation that participants act rationally. The key idea is to introduce repeated competition for FL so that any rational worker follows the protocol and maximize their profits. With mechanism design, we propose a generic full-fledged protocol design for FL on a public blockchain. We also theoretically clarify incentive compatibility based on contest theory which is an auction-based game theory in economics.Keywords
This publication has 12 references indexed in Scilit:
- Federated Machine LearningACM Transactions on Intelligent Systems and Technology, 2019
- Blockchain for AI: Review and Open Research ChallengesIEEE Access, 2019
- Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case StudyApplied Sciences, 2018
- When Machine Learning Meets Blockchain: A Decentralized, Privacy-preserving and Secure Design2018
- On Enabling Machine Learning Tasks atop Public Blockchains: A Crowdsourcing Approach2018
- Transform Blockchain into Distributed Parallel Computing Architecture for Precision Medicine2018
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- ELK, a new protocol for efficient large-group key distribution2002
- The Optimal Allocation of Prizes in ContestsAmerican Economic Review, 2001
- OPTIMAL CONTESTSEconomic Inquiry, 1988