Federated Learning

Chapter 8: Fairness in federated learning

Xiaoqiang Lin^a; Xinyi Xu^a; Zhaoxuan Wu^a; Rachael Hwee Ling Sim^a; See-Kiong Ng^a; Chuan-Sheng Foo^a; Patrick Jaillet^b; Trong Nghia Hoang^c; Bryan Kian Hsiang Low^a    aNational University of Singapore, Singapore, Singapore^bMassachusetts Institute of Technology, Cambridge, MA, United States^cWashington State University, Pullman, WA, United States

Abstract

Federated learning (FL) enables a form of collaboration among multiple clients in jointly learning a machine learning (ML) model without centralizing their local datasets. Like in any collaboration, it is imperative to guarantee fairness so that the clients are willing to participate. For instance, it is unfair if one client benefits significantly more than others, ...