Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Dai Quoc Nguyen, Thanh Vu, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung• 2018

Related benchmarks

TaskDatasetResultRank
Link PredictionFB15k-237 (test)
Hits@1035.6
419
Link PredictionWN18RR (test)
Hits@1055.9
380
Link PredictionFB15k-237
MRR15
280
Knowledge Graph CompletionFB15k-237 (test)
MRR0.523
179
Knowledge Graph CompletionWN18RR (test)
MRR0.415
177
Link PredictionWN18RR
Hits@1055.9
175
Search PersonalizationSEARCH 17 (test)
MRR76.6
7
Showing 7 of 7 rows

Other info

Code

Follow for update