Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
Abstract
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.
Cite
@article{arxiv.2110.02834,
title = {Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations},
author = {Yihong Chen and Pasquale Minervini and Sebastian Riedel and Pontus Stenetorp},
journal= {arXiv preprint arXiv:2110.02834},
year = {2021}
}
Comments
AKBC 2021