Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction

Authors

  • Yao Zhang Nankai university
  • Xu Zhang Nankai university
  • Jun Wang Ludong University
  • Hongru Liang Nankai University
  • Wenqiang Lei National University of Singapore
  • Zhe Sun RIKEN
  • Adam Jatowt University of Innsbruck
  • Zhenglu Yang Nankai University

Keywords:

Linked Open Data, Knowledge Graphs & KB Completio

Abstract

Developing link prediction models to automatically complete knowledge graphs has recently been the focus of significant research interest. The current methods for the link prediction task have two natural problems: 1) the relation distributions in KGs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations. These two problems limit the training effectiveness and practical applications of the existing link prediction models. We advocate a holistic understanding of KGs and we propose in this work a unified Generalized Relation Learning framework GRL to address the above two problems, which can be plugged into existing link prediction models. GRL conducts a generalized relation learning, which is aware of semantic correlations between relations that serve as a bridge to connect semantically similar relations. After training with GRL, the closeness of semantically similar relations in vector space and the discrimination of dissimilar relations are improved. We perform comprehensive experiments on six benchmarks to demonstrate the superior capability of GRL in the link prediction task. In particular, GRL is found to enhance the existing link prediction models making them insensitive to unbalanced relation distributions and capable of learning unseen relations.

Downloads

Published

2021-05-18

How to Cite

Zhang, Y., Zhang, X., Wang, J., Liang, H., Lei, W., Sun, Z., Jatowt, A., & Yang, Z. (2021). Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4679-4687. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16598

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management