Year: 2019
Type: conference-paper
Abstract: 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.
Authors: Guan Wang, Charlie Xiaoqian Dang, Ziye Zhou
Institutions: Swiss Re (Switzerland), Ping An (China)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2974863410
