GLSEC: Global and local semantic-enhanced contrastive framework for knowledge graph completion

Abstract

Knowledge graph completion (KGC) aims to infer missing links between entities in knowledge graphs (KGs). Recently, models based on graph neural networks (GNNs) have gained widespread attention due to their effectiveness in leveraging the topological structure information of entities. Meanwhile, contrastive learning (CL) has been employed in GNNs-based models to provide more supervised signals for better entity representation in a self-supervised manner. However, existing methods overlook the potential global semantic collaboration among entities within the entire KG. And the application of CL in KGC models often adopt random graph augmentation or basic node structure contrast, leading to suboptimal performance. To tackle them, we propose a Global and Local Semantic-Enhanced Contrastive Framework (GLSEC) for KGC. Specifically, we develop a global Attribute-aware encoder to capture the global semantic features of entities based on an entity-entity Attribute Interaction Graph (AIG). Additionally, we design a Light Graph Aggregation Network (Light-GAN) that innovatively updates the global semantic features using the AIG, combining both efficiency and a lightweight design. Furthermore, we introduce a Global-Local cross-view Contrastive Learning (GLCL) method that contrasts embeddings from global and local views, thereby improving contrastive sample quality and boosting the model’s understanding of entities in various contexts. Extensive experiments show that our model outperforms state-of-the-art KGC methods on benchmark datasets FB15k-237 and WN18RR.