University of Oulu

S. R. Pandey, N. H. Tran, M. Bennis, Y. K. Tun, Z. Han and C. S. Hong, "Incentivize to Build: A Crowdsourcing Framework for Federated Learning," 2019 IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA, 2019, pp. 1-6, https://doi.org/10.1109/GLOBECOM38437.2019.9014329

Incentivize to build : a crowdsourcing framework for federated learning

Saved in:
Author: Pandey, Shashi Raj1; Tran, Nguyen H.2; Bennis, Mehdi1,3;
Organizations: 1Department of Computer Science and Engineering, Kyung Hee University, 17104, Rep. of Korea
2School of Computer Science, The University of Sydney, NSW 2006, Australia
3Centre for Wireless Communications, University of Oulu, 90014 Oulu, Finland
4Department of Electrical and Computer Engineering, University of Houston, Houston, TX 77004-4005 USA
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.4 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2020050525025
Language: English
Published: Institute of Electrical and Electronics Engineers, 2019
Publish Date: 2020-05-05
Description:

Abstract

Federated learning (FL) rests on the notion of training a global model in a decentralized manner. Under this setting, mobile devices perform computations on their local data before uploading the required updates to the central aggregator for improving the global model. However, a key challenge is to maintain communication efficiency (i.e., the number of communications per iteration) when participating clients implement uncoordinated computation strategy during aggregation of model parameters. We formulate a utility maximization problem to tackle this difficulty, and propose a novel crowdsourcing framework, involving a number of participating clients with local training data to leverage FL. We show the incentive-based interaction between the crowdsourcing platform and the participating client’s independent strategies for training a global learning model, where each side maximizes its own benefit. We formulate a two-stage Stackelberg game to analyze such scenario and find the game’s equilibria. Further, we illustrate the efficacy of our proposed framework with simulation results. Results show that the proposed mechanism outperforms the heuristic approach with up to 22% gain in the offered reward to attain a level of target accuracy.

see all

Series: IEEE Global Communications Conference
ISSN: 2334-0983
ISSN-E: 2576-6813
ISSN-L: 2334-0983
ISBN: 978-1-7281-0962-6
ISBN Print: 978-1-7281-0963-3
Article number: 9014329
DOI: 10.1109/GLOBECOM38437.2019.9014329
OADOI: https://oadoi.org/10.1109/GLOBECOM38437.2019.9014329
Host publication: 2019 IEEE Global Communications Conference, GLOBECOM 2019
Conference: IEEE Global Communications Conference
Type of Publication: A4 Article in conference proceedings
Field of Science: 213 Electronic, automation and communications engineering, electronics
Subjects:
Funding: The research is partially supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019-0-01287, Evolvable Deep Learning Model Generation Platform for Edge Computing), US MURI AFOSR MURI 18RT0073, NSF CNS-1717454, CNS- 1731424, CNS-1702850, CNS-1646607. Dr. CS Hong is the corresponding author
Copyright information: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.