Relation Prediction in Knowledge Graph by Deep Neural Network

Tracking #: 1842-3055

This paper is currently under review
Yohei Onuki
Murata Tsuyoshi
Nukui Shun
Inagi Seiya
Qiu Xule
Watanabe Masao
Okamoto Hiroshi

Responsible editor: 
Guest Editors Semantic Deep Learning 2018

Submission type: 
Full Paper
The goal of our research is to predict a relation (predicate) of two given Knowledge Graph (KG) entities (subject and object). Link prediction between entities is important for developing large-scale ontologies and for KG completion. TransE and TransR have been proposed as the methods for such a prediction.However, TransE and TransR embed both entities and relations in the same (or different) semantic space(s). Since entity embedding is enough for predicting relations, we propose a method for predicting a predicate from a subject and an object by using a Deep Neural Network (DNN), and developed RDFDNN. RDFDNN embeds entities only; given subject and object are embedded and concatenated to predict probability distribution of predicates. Experimental results showed that predictions by RDFDNN are more accurate than those by TransE and TransR. Although RDFDNN learns from KG triples only, its accuracy is comparable to that of DKRL which uses both KG triples and entity descriptions for learning. RDFDNN is comparable to PTransE in its accuracy and its learning speed is faster than PTransE. The code of RDFDNN is available at
Full PDF Version: 
Under Review