Chen, Yihong;
Minervini, Pasquale;
Riedel, Sebastian;
Stenetorp, Pontus;
(2021)
Relation Prediction as an Auxiliary Training Objective
for Improving Multi-Relational Graph Representations.
In:
Proceedings of the 3rd Conference on Automated Knowledge Base Construction (AKBC).
Automated Knowledge Base Construction (AKBC): Virtual conference.
Preview |
Text
relation_prediction_as_an_auxi.pdf - Published Version Download (890kB) | Preview |
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations |
| Event: | AKBC 2021 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://www.akbc.ws/2021/cfp/ |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | cs.CL, cs.CL, cs.AI |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10154327 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
