A shallow neural model for relation prediction

by   Caglar Demir, et al.

Knowledge graph completion refers to predicting missing triples. Most approaches achieve this goal by predicting entities, given an entity and a relation. We predict missing triples via the relation prediction. To this end, we frame the relation prediction problem as a multi-label classification problem and propose a shallow neural model (SHALLOM) that accurately infers missing relations from entities. SHALLOM is analogous to C-BOW as both approaches predict a central token (p) given surrounding tokens ((s,o)). Our experiments indicate that SHALLOM outperforms state-of-the-art approaches on the FB15K-237 and WN18RR with margins of up to 3% and 8% (absolute), respectively, while requiring a maximum training time of 8 minutes on these datasets. We ensure the reproducibility of our results by providing an open-source implementation including training and evaluation scripts at <https://github.com/dice-group/Shallom>.


page 1

page 2

page 3

page 4


Convolutional Complex Knowledge Graph Embeddings

In this paper, we study the problem of learning continuous vector repres...

DSKG: A Deep Sequential Model for Knowledge Graph Completion

Knowledge graph (KG) completion aims to fill the missing facts in a KG, ...

Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences

Incorporating knowledge graph (KG) into recommender system is promising ...

Information Prediction using Knowledge Graphs for Contextual Malware Threat Intelligence

Large amounts of threat intelligence information about mal-ware attacks ...

Type-augmented Relation Prediction in Knowledge Graphs

Knowledge graphs (KGs) are of great importance to many real world applic...

CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning

Joint extraction of entities and relations has received significant atte...

Probabilistic Belief Embedding for Knowledge Base Completion

This paper contributes a novel embedding model which measures the probab...