Measure Contribution of Participants in Federated Learning

TL;DR

This paper introduces methods to fairly quantify individual participant contributions in federated learning, aiding equitable credit distribution in collaborative model development.

Contribution

It develops novel techniques for contribution measurement in both horizontal and vertical federated learning settings, using deletion methods and Shapley Values.

Findings

Effective calculation of participant influence in horizontal FML.

Accurate assessment of feature importance in vertical FML.

Facilitates fair credit allocation among federated learning participants.

Abstract

Federated Machine Learning (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.