Price of Stability in Quality-Aware Federated Learning

Yan, Yizhou1; Tang, Xinyu1; Huang, Chao2; Tang, Ming1

10.1109/GLOBECOM54140.2023.10437743

2023

IEEE Conference on Global Communications (IEEE GLOBECOM) - Intelligent Communications for Shared Prosperity

2334-0983

2576-6813

IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM

DEC 04-08, 2023

null,Kuala Lumpur,MALAYSIA

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Federated Learning (FL) is a distributed machine learning scheme that enables clients to train a shared global model without exchanging local data. The presence of label noise can severely degrade the FL performance, and some existing studies have focused on algorithm design for label denoising. However, they ignored the important issue that clients may not apply costly label denoising strategies due to them being self-interested and having heterogeneous valuations on the FL performance. To fill this gap, we model the clients' interactions as a novel label denoising game and characterize its equilibrium. We also analyze the price of stability, which quantifies the difference in the system performance (e.g., global model accuracy, social welfare) between the equilibrium outcome and the socially optimal solution. We prove that the equilibrium outcome always leads to a lower global model accuracy than the socially optimal solution does. We further design an efficient algorithm to compute the socially optimal solution. Numerical experiments on MNIST dataset show that the price of stability increases as the clients' data become noisier, calling for an effective incentive mechanism.

第一

英语

CPCI-S

Guangdong Basic and Applied Basic Research Foundation[2023A1515012819] ; National Natural Science Foundation of China[62202214]

Engineering ; Telecommunications

Engineering, Electrical & Electronic ; Telecommunications

WOS:001178562001046

Web of Science

1.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China
2.Univ Calif Davis, Dept Comp Sci, Davis, CA 95616 USA

Yan, Yizhou,Tang, Xinyu,Huang, Chao,et al. Price of Stability in Quality-Aware Federated Learning[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2023.