.png){kind=icon}
.png){kind=icon}
Return
DACHA: A Dual Graph Convolution Based Temporal Knowledge Graph Representation Learning Method Using Historical Relation
.png){kind=icon}
PRE
AI
DOI：10.1145/3477051.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Temporal knowledge graph (TKG) representation learning embeds relations and entities into a continuous low-dimensional vector space by incorporating temporal information. Latest studies mainly aim at learning entity representations by modeling entity interactions from the neighbor structure of the graph. However, the interactions of relations from the neighbor structure of the graph are neglected, which are also of significance for learning informative representations. In addition, there still lacks an effective historical relation encoder tomodel themulti-range temporal dependencies. In this article, we propose a dual graph convolution network based TKG representation learning method using historical relations (DACHA). Specifically, we first construct the primal graph according to historical relations, as well as the edge graph by regarding historical relations as nodes. Then, we employ the dual graph convolution network to capture the interactions of both entities and historical relations from the neighbor structure of the graph. In addition, the temporal self-attentive historical relation encoder is proposed to explicitly model both local and global temporal dependencies. Extensive experiments on two event based TKG datasets demonstrate that DACHA achieves the state-of-the-art results.
Keywords:
Temporal knowledge graph
representation learning
dual graph convolution
Journal
IF:
4.8
Papers:
1.3K
Citations:
4.4K