Temporal knowledge graph embedding via sparse transfer matrix

Knowledge Graph Completion (KGC) is a fundamental problem for temporal knowledge graphs (TKGs), and TKGs embedding methods are one of the essential methods for KGC. However, existing TKG embedding methods encounter a scalability dilemma, i.e., the inconsistency in parameter scalability among different datasets, and the less use of global information, e.g., statistics and dependencies of facts. To mitigate these two issues, we pro-pose a novel and effective TKG embedding method, named Temporal Knowledge Graph Embedding via Sparse Transfer Matrix (TASTER), which provides a framework to utilize both global and local information. Regarding a TKG as a static knowledge graph when ignoring the time dimension, TASTER first learns global embeddings based on this static knowledge graph to capture global information. To capture the local information in a speci-fic timestamp, TASTER evolves local embeddings from global embeddings based on the cor-responding subgraph. Besides, TASTER learns evolving entity embeddings through sparse transformation matrices, which could better adapt to TKGs with a varied number of sub -graphs. We conduct experiments on three real-world datasets, and TASTER outperforms most existing models on the link prediction task of TKGs, which validates the its effectiveness.(c) 2022 Elsevier Inc. All rights reserved.

Automated summary

Knowledge Graph Completion (KGC) is a fundamental problem for temporal knowledge graphs (TKGs), and existing TKG embedding methods face scalability issues and lack of global information utilization. To address these issues, we propose a novel and effective TKG embedding method called Temporal Knowledge Graph Embedding via Sparse Transfer Matrix (TASTER), which combines global and local information. TASTER learns global embeddings from a static knowledge graph and derives local embeddings from global embeddings based on specific subgraphs. It also utilizes sparse transformation matrices to adapt to TKGs with varying subgraphs. Experimental results on real-world datasets demonstrate that TASTER outperforms existing models in TKG link prediction tasks, validating its effectiveness.