Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107084
Title: | Learning task-oriented communication for edge inference : an information bottleneck approach | Authors: | Shao, J Mao, Y Zhang, J |
Issue Date: | Jan-2022 | Source: | IEEE journal on selected areas in communications, Jan. 2022, v. 40, no. 1, p. 197-211 | Abstract: | This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data into an informative and compact representation for low-latency inference given the limited bandwidth. We propose a learning-based communication scheme that jointly optimizes feature extraction, source coding, and channel coding in a task-oriented manner, i.e., targeting the downstream inference task rather than data reconstruction. Specifically, we leverage an information bottleneck (IB) framework to formalize a rate-distortion tradeoff between the informativeness of the encoded feature and the inference performance. As the IB optimization is computationally prohibitive for the high-dimensional data, we adopt a variational approximation, namely the variational information bottleneck (VIB), to build a tractable upper bound. To reduce the communication overhead, we leverage a sparsity-inducing distribution as the variational prior for the VIB framework to sparsify the encoded feature vector. Furthermore, considering dynamic channel conditions in practical communication systems, we propose a variable-length feature encoding scheme based on dynamic neural networks to adaptively adjust the activated dimensions of the encoded feature to different channel conditions. Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions. | Keywords: | Edge inference Information bottleneck Task-oriented communication Variational inference |
Publisher: | Institute of Electrical and Electronics Engineers | Journal: | IEEE journal on selected areas in communications | ISSN: | 0733-8716 | DOI: | 10.1109/JSAC.2021.3126087 | Rights: | © 2021 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 following publication J. Shao, Y. Mao and J. Zhang, "Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach," in IEEE Journal on Selected Areas in Communications, vol. 40, no. 1, pp. 197-211, Jan. 2022 is available at https://doi.org/10.1109/JSAC.2021.3126087. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Shao_Learning_Task-Oriented_Communication.pdf | Preprint version | 1.19 MB | Adobe PDF | View/Open |
Page views
5
Citations as of Jun 30, 2024
Downloads
2
Citations as of Jun 30, 2024
SCOPUSTM
Citations
71
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
50
Citations as of Jun 27, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.