RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs
Buchtitel: IJCKG: International Joint Conference on Knowledge Graphs
Verlag: Association for Computing Machinery
Erscheinungsort: New York, NY, United States
Due to the open world assumption, Knowledge Graphs (KGs) are never complete. In order to address this issue, various Link Pre- diction (LP) methods are proposed so far. Some of these methods are inductive LP models which are capable of learning representa- tions for entities not seen during training. However, to the best of our knowledge, none of the existing inductive LP models focus on learning representations for unseen relations. In this work, a novel Relation Aware Inductive Link preDiction (RAILD) is proposed for KG completion which learns representations for both unseen enti- ties and unseen relations. In addition to leveraging textual literals associated with both entities and relations by employing language models, RAILD also introduces a novel graph-based approach to generate features for relations. Experiments are conducted with dif- ferent existing and newly created challenging benchmark datasets and the results indicate that RAILD leads to performance improve- ment over the state-of-the-art models. Moreover, since there are no existing inductive LP models which learn representations for unseen relations, we have created our own baselines and the results obtained with RAILD also outperform these baselines.