Representation Learning via Variational Bayesian Networks

Oren Barkan, Avi Caciularu, Idan Rejwan, Ori Katz, Jonathan Weill, Itzik Malkiel, Noam Koenigstein

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

Abstract

We present Variational Bayesian Network (VBN) - a novel Bayesian entity representation learning model that utilizes hierarchical and relational side information and is particularly useful for modeling entities in the "long-tail'', where the data is scarce. VBN provides better modeling for long-tail entities via two complementary mechanisms: First, VBN employs informative hierarchical priors that enable information propagation between entities sharing common ancestors. Additionally, VBN models explicit relations between entities that enforce complementary structure and consistency, guiding the learned representations towards a more meaningful arrangement in space. Second, VBN represents entities by densities (rather than vectors), hence modeling uncertainty that plays a complementary role in coping with data scarcity. Finally, we propose a scalable Variational Bayes optimization algorithm that enables fast approximate Bayesian inference. We evaluate the effectiveness of VBN on linguistic, recommendations, and medical inference tasks. Our findings show that VBN outperforms other existing methods across multiple datasets, and especially in the long-tail.

Original languageEnglish
Title of host publicationCIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management
Place of PublicationNew York, NY, USA
Pages78-88
Number of pages11
ISBN (Electronic)9781450384469
DOIs
StatePublished - 26 Oct 2021
Event30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, Australia
Duration: 1 Nov 20215 Nov 2021

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference30th ACM International Conference on Information and Knowledge Management, CIKM 2021
Country/TerritoryAustralia
CityVirtual, Online
Period1/11/215/11/21

Keywords

  • approximate bayesian inference
  • bayesian hierarchical models
  • collaborative filtering
  • deep learning
  • medical informatics
  • natural language processing
  • recommender systems
  • representation learning
  • variational bayesian networks

All Science Journal Classification (ASJC) codes

  • General Decision Sciences
  • General Business,Management and Accounting

Fingerprint

Dive into the research topics of 'Representation Learning via Variational Bayesian Networks'. Together they form a unique fingerprint.

Cite this