Knowledge Graph Completion via Subgraph Topology Augmentation

Knowledge graph completion (KGC) has achieved widespread success as a key technique to ensure high-quality structured knowledge for downstream tasks (e.g., recommendation systems and question answering). However, within the two primary categories of KGC algorithms, the embedding-based methods lack interpretability and most of them only work in transductive settings, while the rule-based approaches sacrifice expressive power to ensure that the models are interpretable. To address these challenges, we propose KGC-STA, a knowledge graph completion method via subgraph topology augmentation. First, KGC-STA contains two topological augmentations for the enclosing subgraphs, including the missing relation completion for sparse nodes and the removal of redundant nodes. Therefore, the augmented subgraphs can provide more useful information. Then a message-passing layer for multi-relation is designed to efficiently aggregate and learn the surrounding information of nodes in the subgraph for triplet scoring. Experimental results in WN18RR and FB15k-237 show that KGC-STA outperforms other baselines and shows higher effectiveness.