A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization
About
In this paper, we introduce an embedding model, named CapsE, exploring a capsule network to model relationship triples (subject, relation, object). Our CapsE represents each triple as a 3-column matrix where each column vector represents the embedding of an element in the triple. This 3-column matrix is then fed to a convolution layer where multiple filters are operated to generate different feature maps. These feature maps are reconstructed into corresponding capsules which are then routed to another capsule to produce a continuous vector. The length of this vector is used to measure the plausibility score of the triple. Our proposed CapsE obtains better performance than previous state-of-the-art embedding models for knowledge graph completion on two benchmark datasets WN18RR and FB15k-237, and outperforms strong search personalization baselines on SEARCH17.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Link Prediction | FB15k-237 (test) | Hits@1035.6 | 419 | |
| Link Prediction | WN18RR (test) | Hits@1055.9 | 380 | |
| Link Prediction | FB15k-237 | MRR15 | 280 | |
| Knowledge Graph Completion | FB15k-237 (test) | MRR0.523 | 179 | |
| Knowledge Graph Completion | WN18RR (test) | MRR0.415 | 177 | |
| Link Prediction | WN18RR | Hits@1055.9 | 175 | |
| Search Personalization | SEARCH 17 (test) | MRR76.6 | 7 |