Skip to main navigation Skip to search Skip to main content

On link prediction in knowledge bases: Max-K criterion and prediction protocols

  • Beihang University
  • University of Ottawa

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

Abstract

Building knowledge base embedding models for link prediction has achieved great success. We however argue that the conventional top-k criterion used for evaluating the model performance is inappropriate. This paper introduces a new criterion, referred to as max-k. Through theoretical analysis and experimental study, we show that the top-k criterion is fundamentally inferior to max-k. We also introduce two prediction protocols for the max-k criterion. These protocols are strongly justified theoretically. Various insights concerning the max-k criterion and the two protocols are obtained through extensive experiments.

Original languageEnglish
Title of host publication41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018
PublisherAssociation for Computing Machinery, Inc
Pages755-764
Number of pages10
ISBN (Electronic)9781450356572
DOIs
StatePublished - 27 Jun 2018
Event41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018 - Ann Arbor, United States
Duration: 8 Jul 201812 Jul 2018

Publication series

Name41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018

Conference

Conference41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018
Country/TerritoryUnited States
CityAnn Arbor
Period8/07/1812/07/18

Keywords

  • Evaluation metric
  • Knowledge base embedding
  • Link prediction

Fingerprint

Dive into the research topics of 'On link prediction in knowledge bases: Max-K criterion and prediction protocols'. Together they form a unique fingerprint.

Cite this