Learning Multi-Rate Vector Quantization for Remote Deep Inference

May Malka, Shai Ginzach, Nir Shlezinger

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Remote inference accommodates a broad range of scenarios, where inference is carried out using data acquired at a remote user. When the sensing and inferring users communicate over rate limited channels, compression of the data reduces latency, and deep learning enables to jointly learn the compression encoding along with the inference rule. However, because the data is compressed into a fixed number of bits, the resolution cannot be adapted to changes in channel conditions. In this work we propose a multi-rate remote deep inference scheme, which trains a single encoder-decoder model that uses learned vector quantizers while supporting different quantization levels. Our scheme is based on designing nested codebooks along with a learning algorithm based on progressive learning. Numerical results demonstrate that the proposed scheme yields remote deep inference that operates with multiple rates while approaching the performance of fixed-rate models.

Original languageEnglish
Title of host publicationICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings
PublisherInstitute of Electrical and Electronics Engineers
ISBN (Electronic)9798350302615
DOIs
StatePublished - 1 Jan 2023
Event2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023 - Rhodes Island, Greece
Duration: 4 Jun 202310 Jun 2023

Publication series

NameICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings

Conference

Conference2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023
Country/TerritoryGreece
CityRhodes Island
Period4/06/2310/06/23

Keywords

  • Remote inference
  • adaptive compression

ASJC Scopus subject areas

  • Computer Science Applications
  • Acoustics and Ultrasonics
  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Learning Multi-Rate Vector Quantization for Remote Deep Inference'. Together they form a unique fingerprint.

Cite this