Temporal-structural importance weighted graph convolutional network for temporal knowledge graph completion

Abstract

Knowledge graph completion (KGC) tasks are aimed to reason out missing facts in a knowledge graph. However, knowledge often evolves over time, and static knowledge graph completion methods have difficulty in identifying its changes. Scholars have focus on temporal knowledge graph completion (TKGC). Most existing TKGC methods incorporate temporal information into triples and convert them into KGC tasks, ignoring the impact of temporal information on quaternions. Furthermore, existing embedding learning methods based on message-passing network aggregate features passed by neighbors with the same attention, ignoring the complex structure information that each node has different importance in passing the message. Therefore, to capture the impact of temporal information on quaternions and structural information on nodes, we proposed a TKGC method based on temporal attention learning (TAL-TKGC), which includes a temporal attention module and an importance-weighted GCN. The temporal attention module was designed to capture the deep connection between timestamps entities and relations at the semantic levels. The importance-weighted GCN considers the structural importance and attention of temporal information to entities for weighted aggregation. Finally, we conducted experiments on two public datasets, and the results proved the performance of our method. We also performed the speedup experiments in a distributed environment, and the proposed model has an excellent scalability on multiple GPUs.