Towards Efficient Edge Learning with Limited Storage Resource: Bandit-Based Training Data Retrieval in AIoT
Document Type
Conference Proceeding
Publication Date
1-1-2024
Abstract
In an intelligent IoT environment, an edge server needs to retrieve data from end devices to train the deep neural network deployed at edge. In order to achieve higher training performance with limited resources, we propose a Bandit-based in-network training data retrieval scheme(Bandit-TDRetrieval). Specifically, we formulate data retrieval from end devices with a multi-armed bandit (MAB) model. A sequence of lever pulls of the arms, indicates the options to retrieve data from different end devices and follows a binomial distribution. To identify the relationship between this binomial distribution and the rewards through continuous data retrieval from the corresponding devices, Thompson sampling is used. In this way, an efficient data retrieval paradigm is proposed to maximize the rewards to retrieve meaningful training data for edge learning. Finally, the evaluations are performed on a NS-3-based simulation platform, which demonstrate the proposed paradigm effectively improve the training efficiency of the deep neural networks at edge.
Identifier
85184796955 (Scopus)
ISBN
[9783031477140]
Publication Title
Lecture Notes in Networks and Systems
External Full Text Location
https://doi.org/10.1007/978-3-031-47715-7_39
e-ISSN
23673389
ISSN
23673370
First Page
571
Last Page
588
Volume
824 LNNS
Fund Ref
Beijing University of Posts and Telecommunications
Recommended Citation
Wang, Jing; Liu, Siyuan; Liu, Wenjing; Xu, Zhiwei; Zhang, Jiaqi; and Tian, Jie, "Towards Efficient Edge Learning with Limited Storage Resource: Bandit-Based Training Data Retrieval in AIoT" (2024). Faculty Publications. 1090.
https://digitalcommons.njit.edu/fac_pubs/1090