Deep clustering of compressed variational embeddings

Suya Wu, Enmao Diao, Jie Ding, Vahid Tarokh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Motivated by the ever-increasing demands for limited communication bandwidth and low-power consumption, we propose a new methodology, named joint Variational Autoencoders with Bernoulli mixture models (VAB), for performing clustering in the compressed data domain. The idea is to reduce the data dimension by Variational Autoencoders (VAEs) and group data representations by Bernoulli mixture models (BMMs). Once jointly trained for compression and clustering, the model can be decomposed into two parts: a data vendor that encodes the raw data into compressed data, and a data consumer that classifies the received (compressed) data. In this way, the data vendor benefits from data security and communication bandwidth, while the data consumer benefits from low computational complexity. To enable training using the gradient descent algorithm, we propose to use the Gumbel-Softmax distribution to resolve the infeasibility of the back-propagation algorithm when assessing categorical samples.

Original languageEnglish (US)
Title of host publicationProceedings - DCC 2020
Subtitle of host publicationData Compression Conference
EditorsAli Bilgin, Michael W. Marcellin, Joan Serra-Sagrista, James A. Storer
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages399
Number of pages1
ISBN (Electronic)9781728164571
DOIs
StatePublished - Mar 2020
Event2020 Data Compression Conference, DCC 2020 - Snowbird, United States
Duration: Mar 24 2020Mar 27 2020

Publication series

NameData Compression Conference Proceedings
Volume2020-March
ISSN (Print)1068-0314

Conference

Conference2020 Data Compression Conference, DCC 2020
CountryUnited States
CitySnowbird
Period3/24/203/27/20

Bibliographical note

Funding Information:
This work was mostly done when Suya Wu was a student at the University of Minnesota. She is now with Duke University. This work was supported in part by Office of Naval Research Grant No. N00014-18-1-2244.

Publisher Copyright:
© 2020 IEEE.

Keywords

  • Bernoulli mixture model (BMM)
  • Clustering
  • Variational autoencoder (VAE)

Fingerprint Dive into the research topics of 'Deep clustering of compressed variational embeddings'. Together they form a unique fingerprint.

Cite this