Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs

The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN) based models generate richer and more expressive feature embeddings and hence also perform well on relation prediction. However, we observe that these KG embeddings treat triples independently and thus fail to cover the complex and hidden information that is inherently implicit in the local neighborhood surrounding a triple. To this effect, our paper proposes a novel attention based feature embedding that captures both entity and relation features in any given entity's neighborhood. Additionally, we also encapsulate relation clusters and multihop relations in our model. Our empirical study offers insights into the efficacy of our attention based model and we show marked performance gains in comparison to state of the art methods on all datasets.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Knowledge Graph Completion FB15k-237 KBGAT Hits@3 54 # 1
Hits@10 62.6 # 1
Knowledge Graph Completion FB15k-237 KBAT Hits@1 46 # 1
MRR 0.518 # 1
MR 0.210 # 1
Link Prediction WN18RR KBGAT Hits@10 0.581 # 14
Hits@3 0.483 # 28
Hits@1 0.361 # 45
Link Prediction WN18RR KBAT MRR 0.44 # 49
Hits@1 0.361 # 45
MR 1940.0 # 10


No methods listed for this paper. Add relevant methods here