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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Link Prediction | FB15k-237 (test) | Hits@1056.8 | 419 | |
| Link Prediction | WN18RR (test) | Hits@1058 | 380 | |
| Link Prediction | FB15k-237 | -- | 280 | |
| Knowledge Graph Completion | FB15k-237 (test) | MRR0.388 | 179 | |
| Knowledge Graph Completion | WN18RR (test) | MRR0.488 | 177 | |
| Link Prediction | WN18RR | Hits@1058 | 175 | |
| Link Prediction | ogbl-wikikg2 (test) | MRR0.6481 | 95 | |
| Link Prediction | ogbl-wikikg2 (val) | MRR0.6701 | 87 | |
| Link Prediction | UMLS | Hits@1099.8 | 56 | |
| Link Prediction | ogbl-biokg (test) | MRR0.8494 | 36 |