Task-Oriented Communication for Multi-Device Cooperative Edge Inference

Jiawei Shao, Yuyi Mao, Jun Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

25 Citations (Scopus)


This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-end edge devices transmit the extracted features of local samples to a powerful edge server for inference. While cooperative edge inference can overcome the limited sensing capability of a single device, it substantially increases the communication overhead and may incur excessive latency. To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a <italic>task-oriented</italic> manner, i.e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server. Specifically, we leverage Tishby&#x2019;s information bottleneck (IB) principle [1] to extract the task-relevant feature at each edge device, and adopt the distributed information bottleneck (DIB) framework of Aguerri-Zaidi [2] to formalize a single-letter characterization of the optimal rate-relevance tradeoff for distributed feature encoding. To admit flexible control of the communication overhead, we extend the DIB framework to a distributed deterministic information bottleneck (DDIB) objective that explicitly incorporates the representational costs of the encoded features. As the IB-based objectives are computationally prohibitive for high-dimensional data, we adopt variational approximations to make the optimization problems tractable. To compensate for the potential performance loss due to the variational approximations, we also develop a selective retransmission (SR) mechanism to identify the redundancy in the encoded features among multiple edge devices to attain additional communication overhead reduction. Extensive experiments on multi-view image classification and multi-view object recognition tasks evidence that the proposed task-oriented communication scheme achieves a better rate-relevance tradeoff than existing methods.

Original languageEnglish
Article number9837474
Pages (from-to)1
Number of pages1
JournalIEEE Transactions on Wireless Communications
Publication statusAccepted/In press - Jul 2022


  • Distributed databases
  • distributed information bottleneck (DIB)
  • Encoding
  • Feature extraction
  • Image edge detection
  • information bottleneck (IB)
  • Performance evaluation
  • Servers
  • Task analysis
  • Task-oriented communication
  • variational inference

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Applied Mathematics


Dive into the research topics of 'Task-Oriented Communication for Multi-Device Cooperative Edge Inference'. Together they form a unique fingerprint.

Cite this