Efficient Client Contribution Evaluation for Horizontal Federated Learning
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3060-3064
Abstract
In federated learning (FL), fair and accurate measurement of the contribution of each federated participant is of great significance. The level of contribution not only provides a rational metric for distributing financial benefits among federated participants, but also helps to discover malicious participants that try to poison the FL framework. Previous methods for contribution measurement were based on enumeration over possible combination of federated participants. Their computation costs increase drastically with the number of participants or feature dimensions, making them inapplicable in practical situations. In this paper an efficient method is proposed to evaluate the contributions of federated participants. This paper focuses on the horizontal FL framework, where client servers calculate parameter gradients over their local data, and upload the gradients to the central server. Before aggregating the client gradients, the central server train a data value estimator of the gradients using reinforcement learning techniques. As shown by experimental results, the proposed method consistently outperforms the conventional leave-one-out method in terms of valuation authenticity as well as time complexity.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China
This publication has 10 references indexed in Scilit:
- FedCoin: A Peer-to-Peer Payment System for Federated Learning2020
- Network Coding for Federated Learning Systems2020
- FedSmart: An Auto Updating Federated Learning Optimization Mechanism2020
- Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework2020
- A Learning-Based Incentive Mechanism for Federated LearningIEEE Internet of Things Journal, 2020
- Measure Contribution of Participants in Federated Learning2019
- Federated Learning of Unsegmented Chinese Text Recognition Model2019
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Contributions to the study of SMS spam filtering2011