An incentive scheme for federated learning in the sky

Wei Yang Bryan Lim; Zehui Xiong; Jiawen Kang; Dusit Niyato; Yang Zhang; Cyril Leung; Chunyan Miao

doi:10.1145/3414045.3415935

An incentive scheme for federated learning in the sky

Wei Yang Bryan Lim
, Zehui Xiong
, Jiawen Kang
, Dusit Niyato
, Yang Zhang
, Cyril Leung
, Chunyan Miao

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Citations (Scopus)

Abstract

The enhanced capabilities of Unmanned Aerial Vehicles have promoted the rapid growth of the Drones-as-a-Service (DaaS) market. To enable privacy-preserving collaborative machine learning among independent DaaS providers, we propose a Federated Learning (FL) based approach. There exists a tradeoff between Service Latency (SL), i.e., the time taken for the training request to be completed, and Age of Information (Aol), i.e., the time elapsed between data aggregation to completion of the FL based training. Given that different training tasks may have varying Aol requirements, we propose a contract-theoretic task-aware incentive scheme that can be calibrated based on the weighted preferences of the model owner. Performance evaluation validates the incentive compatibility and flexibility of our contract design amid information asymmetry.

Original language	English
Title of host publication	DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond
Publisher	Association for Computing Machinery
Pages	55-60
Number of pages	6
ISBN (Electronic)	9781450381055
DOIs	https://doi.org/10.1145/3414045.3415935
Publication status	Published - 07 Oct 2020
Externally published	Yes
Event	2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020 - London, United Kingdom Duration: 25 Sept 2020 → …

Publication series

Name	DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond
Publisher	ACM

Conference

Conference	2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020
Country/Territory	United Kingdom
City	London
Period	25/09/2020 → …

Bibliographical note

Publisher Copyright:
© 2020 Association for Computing Machinery.

Keywords

Federated Learning
Incentive Mechanism
Mobile crowdsensing
Unmanned Aerial Vehicle

ASJC Scopus subject areas

Information Systems
Computer Networks and Communications

Access to Document

10.1145/3414045.3415935Licence: Unspecified

Cite this

Lim, W. Y. B., Xiong, Z., Kang, J., Niyato, D., Zhang, Y., Leung, C., & Miao, C. (2020). An incentive scheme for federated learning in the sky. In DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond (pp. 55-60). (DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond). Association for Computing Machinery. https://doi.org/10.1145/3414045.3415935

Lim, Wei Yang Bryan ; Xiong, Zehui ; Kang, Jiawen et al. / An incentive scheme for federated learning in the sky. DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond. Association for Computing Machinery, 2020. pp. 55-60 (DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond).

@inproceedings{2faa9ac8dfd248eab507534a7c023f06,

title = "An incentive scheme for federated learning in the sky",

abstract = "The enhanced capabilities of Unmanned Aerial Vehicles have promoted the rapid growth of the Drones-as-a-Service (DaaS) market. To enable privacy-preserving collaborative machine learning among independent DaaS providers, we propose a Federated Learning (FL) based approach. There exists a tradeoff between Service Latency (SL), i.e., the time taken for the training request to be completed, and Age of Information (Aol), i.e., the time elapsed between data aggregation to completion of the FL based training. Given that different training tasks may have varying Aol requirements, we propose a contract-theoretic task-aware incentive scheme that can be calibrated based on the weighted preferences of the model owner. Performance evaluation validates the incentive compatibility and flexibility of our contract design amid information asymmetry.",

keywords = "Federated Learning, Incentive Mechanism, Mobile crowdsensing, Unmanned Aerial Vehicle",

author = "Lim, \{Wei Yang Bryan\} and Zehui Xiong and Jiawen Kang and Dusit Niyato and Yang Zhang and Cyril Leung and Chunyan Miao",

note = "Publisher Copyright: {\textcopyright} 2020 Association for Computing Machinery.; 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020 ; Conference date: 25-09-2020",

year = "2020",

month = oct,

day = "7",

doi = "10.1145/3414045.3415935",

language = "English",

series = "DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond",

publisher = "Association for Computing Machinery",

pages = "55--60",

booktitle = "DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond",

address = "United States",

}

Lim, WYB, Xiong, Z, Kang, J, Niyato, D, Zhang, Y, Leung, C & Miao, C 2020, An incentive scheme for federated learning in the sky. in DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond. DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, Association for Computing Machinery, pp. 55-60, 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020, London, United Kingdom, 25/09/2020. https://doi.org/10.1145/3414045.3415935

An incentive scheme for federated learning in the sky. / Lim, Wei Yang Bryan; Xiong, Zehui; Kang, Jiawen et al.
DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond. Association for Computing Machinery, 2020. p. 55-60 (DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An incentive scheme for federated learning in the sky

AU - Lim, Wei Yang Bryan

AU - Xiong, Zehui

AU - Kang, Jiawen

AU - Niyato, Dusit

AU - Zhang, Yang

AU - Leung, Cyril

AU - Miao, Chunyan

PY - 2020/10/7

Y1 - 2020/10/7

N2 - The enhanced capabilities of Unmanned Aerial Vehicles have promoted the rapid growth of the Drones-as-a-Service (DaaS) market. To enable privacy-preserving collaborative machine learning among independent DaaS providers, we propose a Federated Learning (FL) based approach. There exists a tradeoff between Service Latency (SL), i.e., the time taken for the training request to be completed, and Age of Information (Aol), i.e., the time elapsed between data aggregation to completion of the FL based training. Given that different training tasks may have varying Aol requirements, we propose a contract-theoretic task-aware incentive scheme that can be calibrated based on the weighted preferences of the model owner. Performance evaluation validates the incentive compatibility and flexibility of our contract design amid information asymmetry.

AB - The enhanced capabilities of Unmanned Aerial Vehicles have promoted the rapid growth of the Drones-as-a-Service (DaaS) market. To enable privacy-preserving collaborative machine learning among independent DaaS providers, we propose a Federated Learning (FL) based approach. There exists a tradeoff between Service Latency (SL), i.e., the time taken for the training request to be completed, and Age of Information (Aol), i.e., the time elapsed between data aggregation to completion of the FL based training. Given that different training tasks may have varying Aol requirements, we propose a contract-theoretic task-aware incentive scheme that can be calibrated based on the weighted preferences of the model owner. Performance evaluation validates the incentive compatibility and flexibility of our contract design amid information asymmetry.

KW - Federated Learning

KW - Incentive Mechanism

KW - Mobile crowdsensing

KW - Unmanned Aerial Vehicle

U2 - 10.1145/3414045.3415935

DO - 10.1145/3414045.3415935

M3 - Conference contribution

AN - SCOPUS:85097161769

T3 - DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond

SP - 55

EP - 60

BT - DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond

PB - Association for Computing Machinery

T2 - 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020

Y2 - 25 September 2020

ER -

Lim WYB, Xiong Z, Kang J, Niyato D, Zhang Y, Leung C et al. An incentive scheme for federated learning in the sky. In DroneCom 2020: Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond. Association for Computing Machinery. 2020. p. 55-60. (DroneCom 2020 - Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond). doi: 10.1145/3414045.3415935

An incentive scheme for federated learning in the sky

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this