Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
Chen, Yihong, Minervini, Pasquale, Riedel, Sebastian, Stenetorp, Pontus
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-6-2021
- Country:
- Europe > United Kingdom
- England > Greater London > London (0.14)
- North America > United States
- California (0.46)
- New York (0.28)
- Europe > United Kingdom
- Genre:
- Instructional Material (0.84)
- Personal > Honors (1.00)
- Research Report (0.83)
- Industry:
- Leisure & Entertainment > Sports
- Soccer (0.47)
- Media > Film (1.00)
- Leisure & Entertainment > Sports
- Technology: