A Comprehensive Survey of Incentive Mechanism for Federated Learning
arXiv:2106.15406
Abstract
Federated learning utilizes various resources provided by participants to collaboratively train a global model, which potentially address the data privacy issue of machine learning. In such promising paradigm, the performance will be deteriorated without sufficient training data and other resources in the learning process. Thus, it is quite crucial to inspire more participants to contribute their valuable resources with some payments for federated learning. In this paper, we present a comprehensive survey of incentive schemes for federate learning. Specifically, we identify the incentive problem in federated learning and then provide a taxonomy for various schemes. Subsequently, we summarize the existing incentive mechanisms in terms of the main techniques, such as Stackelberg game, auction, contract theory, Shapley value, reinforcement learning, blockchain. By reviewing and comparing some impressive results, we figure out three directions for the future study.
arXiv commentmore than 10 pages
References in corpus (11)
- A Brief Survey of Deep Reinforcement Learning
- Federated Learning for Mobile Keyboard Prediction
- FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC
- Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach
- Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approach
- A VCG-based Fair Incentive Mechanism for Federated Learning
- FedCoin: A Peer-to-Peer Payment System for Federated Learning
- Mechanism Design for Multi-Party Machine Learning
- Incentives for Federated Learning: a Hypothesis Elicitation Approach
- 2CP: Decentralized Protocols to Transparently Evaluate Contributivity in Blockchain Federated Learning Environments
- Joint Service Pricing and Cooperative Relay Communication for Federated Learning