Motivating workers in federated learning: a Stackelberg game perspective

Warning The system is temporarily closed to updates for reporting purpose.

Sarıkaya, Yunus and Erçetin, Özgür (2020) Motivating workers in federated learning: a Stackelberg game perspective. IEEE Networking Letters, 2 (1). pp. 23-27. ISSN 2576-3156

[img]PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1109/LNET.2019.2947144


Due to the large size of the training data, distributed learning approaches such as federated learning have gained attention recently. However, the convergence rate of distributed learning suffers from heterogeneous worker performance. In this letter, we consider an incentive mechanism for workers to mitigate the delays in completion of each batch. We analytically obtained equilibrium solution of a Stackelberg game. Our numerical results indicate that with a limited budget, the model owner should judiciously decide on the number of workers due to trade off between the diversity provided by the number of workers and the latency of completing the training.

Item Type:Article
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication
ID Code:40192
Deposited By:Özgür Erçetin
Deposited On:16 Sep 2020 22:53
Last Modified:16 Sep 2020 22:53

Repository Staff Only: item control page