Measure Contribution of Participants in Federated Learning

--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 V ertical FML we use Shapley V alues 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. I NTRODUCTION Federated Learning or Federated Machine Learning (FML) [1] is introduced to solve privacy issues in machine learning using data from multiple parties.