TBDRI: block decomposition based on relational interaction for temporal knowledge graph completion

Mei Yu

doi:10.1007/s10489-022-03601-5

2022-06-17

PRE

DOI：10.1007/s10489-022-03601-5

原文链接

原文求助

摘要

En 中文

Knowledge graph completion (KGC) can be interpreted as the task of missing inferences to real-world facts. Despite the importance and abundance of temporal knowledge graphs, most of the current research has been focused on reasoning on static knowledge graphs. The data they are applied to usually evolves with time, such as friend graphs in social networks. Therefore, developing temporal knowledge graph completion (temporal KGC) models is an increasingly important topic, although it is difficult due to data non-stationarity, and its complex temporal dependencies. In this paper, we propose block decomposition based on relational interaction for temporal knowledge graph completion (TBDRI), a novel model based on block term decomposition (which can be seen as a special variant of CP decomposition and Tucker decomposition) of the binary tensor representation of knowledge graph quadruples. TBDRI considers that inverse relations, as one of the most important types of relations, occupy an important share in the real world. Although some existing models introduce inverse relation into the model, it is not enough to only learn the inverse relation independently. TBDRI learns inverse relation in an enhanced way to strengthen the binding of forward and inverse relation. Furthermore, TBDRI first uses the core tensor as temporal information to bind timestamps more adequately. We prove TBDRI is full expressiveness and derive the bound on its entity, relation, and timestamp embedding dimensionality. We show that TBDRI is able to outperform most previous state-of-the-art models on the four benchmark datasets for temporal knowledge graph completion.

Keyword:

Temporal KGC

Inverse relation

Tensor decomposition