Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/152724
Title: When information freshness meets service latency in federated learning : a task-aware incentive scheme for smart industries
Authors: Lim, Bryan Wei Yang
Xiong, Zehui
Kang, Jiawei
Niyato, Dusit
Leung, Cyril
Miao, Chunyan
Shen, Xuemin
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Lim, B. W. Y., Xiong, Z., Kang, J., Niyato, D., Leung, C., Miao, C. & Shen, X. (2020). When information freshness meets service latency in federated learning : a task-aware incentive scheme for smart industries. IEEE Transactions On Industrial Informatics, 18(1), 457-466. https://dx.doi.org/10.1109/TII.2020.3046028
Project: AISG-GC-2019-003 
NRF2017EWT-EP003-041 
NRF2015-NRF-ISF001-2277 
M4082187 (4080) 
RG16/20 
Journal: IEEE Transactions on Industrial Informatics 
Abstract: For several industrial applications, a sole data owner may lack sufficient training samples to train effective machine learning based models. As such, we propose a Federated Learning (FL) based approach to promote privacy-preserving collaborative machine learning for applications in smart industries. In our system model, a model owner initiates an FL task involving a group of workers, i.e., data owners, to perform model training on their locally stored data before transmitting the model updates for aggregation. There exists a tradeoff between service latency, i.e., the time taken for the training request to be completed, and Age of Information (AoI), i.e., the time elapsed between data aggregation from the deployed IIoT devices to completion of the FL based training. On one hand, if the data is collected only upon the model owner's request, the AoI is low. On the other hand, the service latency incurred is more significant. Furthermore, given that different training tasks may have varying AoI requirements, we propose a contract-theoretic task-aware incentive scheme that can be calibrated based on the weighted preferences of the model owner towards AoI and service latency. Performance evaluation validates the incentive compatibility of our contract amid information asymmetry, and shows the flexibility of our proposed scheme towards satisfying varying preferences of AoI and service latency.
URI: https://hdl.handle.net/10356/152724
ISSN: 1551-3203
DOI: 10.1109/TII.2020.3046028
Rights: © 2020 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. The published version is available at: https://doi.org/10.1109/TII.2020.3046028.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Page view(s)

38
Updated on May 19, 2022

Download(s) 20

161
Updated on May 19, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.