Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks

Leyla Mirvakhabova, Evgeny Frolov, Valentin Khrulkov, Ivan Oseledets, Alexander Tuzhilin

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

10 Citations (Scopus)

Abstract

We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem. In contrast to many modern deep learning techniques, we build our solution using only a single hidden layer. Remarkably, even with such a minimalistic approach, we not only outperform the Euclidean counterpart but also achieve a competitive performance with respect to the current state-of-the-art. We additionally explore the effects of space curvature on the quality of hyperbolic models and propose an efficient data-driven method for estimating its optimal value.

Original languageEnglish
Title of host publicationRecSys 2020 - 14th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages527-532
Number of pages6
ISBN (Electronic)9781450375832
DOIs
Publication statusPublished - 22 Sep 2020
Event14th ACM Conference on Recommender Systems, RecSys 2020 - Virtual, Online, Brazil
Duration: 22 Sep 202026 Sep 2020

Publication series

NameRecSys 2020 - 14th ACM Conference on Recommender Systems

Conference

Conference14th ACM Conference on Recommender Systems, RecSys 2020
Country/TerritoryBrazil
CityVirtual, Online
Period22/09/2026/09/20

Keywords

  • Autoencoders
  • Collaborative Filtering
  • Hyperbolic Geometry
  • Top-N Recommendation

Fingerprint

Dive into the research topics of 'Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks'. Together they form a unique fingerprint.

Cite this