Motivating workers in federated learning: a Stackelberg game perspective

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

[thumbnail of 08867906.pdf] PDF
08867906.pdf
Restricted to Registered users only

Download (480kB) | Request a copy

Abstract

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
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Electronics
Faculty of Engineering and Natural Sciences
Depositing User: Özgür Erçetin
Date Deposited: 16 Sep 2020 22:53
Last Modified: 16 Sep 2020 22:53
URI: https://research.sabanciuniv.edu/id/eprint/40192

Actions (login required)

View Item
View Item