Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations

About

Learning good representations on multi-relational graphs is essential to knowledge base completion (KBC). In this paper, we propose a new self-supervised training objective for multi-relational graph representation learning, via simply incorporating relation prediction into the commonly used 1vsAll objective. The new training objective contains not only terms for predicting the subject and object of a given triple, but also a term for predicting the relation type. We analyse how this new objective impacts multi-relational learning in KBC: experiments on a variety of datasets and models show that relation prediction can significantly improve entity ranking, the most widely used evaluation task for KBC, yielding a 6.1% increase in MRR and 9.9% increase in Hits@1 on FB15k-237 as well as a 3.1% increase in MRR and 3.4% in Hits@1 on Aristo-v4. Moreover, we observe that the proposed objective is especially effective on highly multi-relational datasets, i.e. datasets with a large number of predicates, and generates better representations when larger embedding sizes are used.

Yihong Chen, Pasquale Minervini, Sebastian Riedel, Pontus Stenetorp• 2021

Related benchmarks

TaskDatasetResultRank
Link PredictionFB15k-237 (test)
Hits@1056.8
419
Link PredictionWN18RR (test)
Hits@1058
380
Link PredictionFB15k-237--
280
Knowledge Graph CompletionFB15k-237 (test)
MRR0.388
179
Knowledge Graph CompletionWN18RR (test)
MRR0.488
177
Link PredictionWN18RR
Hits@1058
175
Link Predictionogbl-wikikg2 (test)
MRR0.6481
95
Link Predictionogbl-wikikg2 (val)
MRR0.6701
87
Link PredictionUMLS
Hits@1099.8
56
Link Predictionogbl-biokg (test)
MRR0.8494
36
Showing 10 of 15 rows

Other info

Code

Follow for update