The Effectiveness of Graph Contrastive Learning on Mathematical Information Retrieval

Pei Syuan Wang, Hung Hsuan Chen

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

Abstract

This paper details an empirical investigation into using Graph Contrastive Learning (GCL) to generate mathematical equation representations, a critical aspect of Mathematical Information Retrieval (MIR). Our findings reveal that this simple approach consistently exceeds the performance of the current leading formula retrieval model, TangentCFT. To support ongoing research and development in this field, we have made our source code accessible to the public at https://github.com/WangPeiSyuan/GCL-Formula-Retrieval/.

Original languageEnglish
Title of host publicationAdvances on Graph-Based Approaches in Information Retrieval - 1st International Workshop, IRonGraphs 2024, Proceedings
EditorsLudovico Boratto, Mirko Marras, Giacomo Medda, Daniele Malitesta, Cataldo Musto, Erasmo Purificato
PublisherSpringer Science and Business Media Deutschland GmbH
Pages60-72
Number of pages13
ISBN (Print)9783031713811
DOIs
StatePublished - 2025
Event1st International Workshop on Graph-Based Approaches in Information Retrieval, IRonGRAPHS 2024 - Glasgow, United Kingdom
Duration: 24 Mar 202424 Mar 2024

Publication series

NameCommunications in Computer and Information Science
Volume2197 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference1st International Workshop on Graph-Based Approaches in Information Retrieval, IRonGRAPHS 2024
Country/TerritoryUnited Kingdom
CityGlasgow
Period24/03/2424/03/24

Keywords

  • Graphical contrastive learning
  • Layout
  • Mathematical information retrieval

Fingerprint

Dive into the research topics of 'The Effectiveness of Graph Contrastive Learning on Mathematical Information Retrieval'. Together they form a unique fingerprint.

Cite this