Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction

TL;DR

This paper introduces a unified framework called GRL that enhances link prediction models by understanding semantic relations, addressing data imbalance and unseen relations, leading to improved knowledge graph completion.

Contribution

The paper proposes a novel Generalized Relation Learning framework that can be integrated into existing models to improve their semantic understanding and handling of unbalanced and unseen relations.

Findings

GRL improves relation discrimination in vector space.

Enhanced models are less sensitive to relation distribution imbalance.

GRL enables learning of unseen relations in knowledge graphs.

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 taskhavetwonaturalproblems: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.