Measure Contribution of Participants in Federated Learning
- Resource Type
- Conference
- Authors
- Wang, Guan; Dang, Charlie Xiaoqian; Zhou, Ziye
- Source
- 2019 IEEE International Conference on Big Data (Big Data) Big Data (Big Data), 2019 IEEE International Conference on. :2597-2604 Dec, 2019
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Computing and Processing
General Topics for Engineers
Geoscience
Signal Processing and Analysis
Transportation
Data models
Machine learning
Biological system modeling
Predictive models
Computational modeling
Google
Approximation algorithms
federated learning
machine learning
deletion
shapley values
- Language
Federated Machine Learnig (FML) creates an ecosystem for multiple parties to collaborate on building models while protecting data privacy for the participants. A measure of the contribution for each party in FML enables fair credits allocation. In this paper we develop simple but powerful techniques to fairly calculate the contributions of multiple parties in FML, in the context of both horizontal FML and vertical FML. For Horizontal FML we use deletion method to calculate the grouped instance influence. For Vertical FML we use Shapley Values to calculate the grouped feature importance. Our methods open the door for research in model contribution and credit allocation in the context of federated machine learning.