.png){kind=icon}
.png){kind=icon}
Return
Recalibration convolutional networks for learning interaction knowledge graph embedding
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2020.07.137.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Knowledge graph embedding aims to learn the embedded representation of entities and relations in knowledge graphs which is very important for the subsequent link prediction task. However, two key issues are existed for learning knowledge graph embedding: 1) How to take full advantage of the deep learning algorithms to generate expressive embeddings? 2) How to solve the polysemy phenomenon caused by multi-relations knowledge graphs that entities and relations show different semantics after involving different predictions? In this article, to tackle the first problem, the multi-layer convolutional networks are adopted to generate features about entities and relations then used to predict candidate entity. Moreover, the representation power of the networks is strengthened by integrating an effective recalibration mechanism which can accentuate informative features selectively. To tackle the second problem, we propose to learn multiple specific interaction embeddings. Instead of directly learning one general embedding to preserve all information for each entity and relation, their interactions are captured to model the cross-semantic influence from relations to entities and from entities to relations. Compared to traditional embedding models, the proposed model can provide more generalization capabilities and effectively capture potential links between entities and relations. Experimental results have revealed that the proposed model achieves the state-of-the-art performance for general evaluation metrics on link prediction tasks. (c) 2020 Elsevier B.V. All rights reserved.
Keywords:
Knowledge graph embedding
Representation learning
Link prediction
Convolutional networks
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W