Federated Learning

Chapter 15: Data valuation in federated learning

Zhaoxuan Wu^a; Xinyi Xu^a; Rachael Hwee Ling Sim^a; Yao Shu^a; Xiaoqiang Lin^a; Lucas Agussurja^a; Zhongxiang Dai^a; See-Kiong Ng^a; Chuan-Sheng Foo^b; Patrick Jaillet^c; Trong Nghia Hoang^d; Bryan Kian Hsiang Low^a    aNational University of Singapore, Singapore, Singapore^bAgency for Science, Technology and Research, Singapore, Singapore^cMassachusetts Institute of Technology, Cambridge, MA, United States^dWashington State University, Pullman, WA, United States

Abstract

Federated learning (FL) has become an increasingly popular solution paradigm for enabling collaborative machine learning (CML) in which multiple clients can collaboratively train a common model without sharing their private training data with others. ...