A paper accepted in IEEE ICDM 2022

Title: THOR: Self-Supervised Temporal Knowledge Graph Embedding via Three-Tower Graph Convolutional Networks
Author: Yeon-Chang Lee*, JaeHyun Lee*, Dongwon Lee, and Sang-Wook Kim
Abstract
The goal of temporal knowledge graph embedding (TKGE) is to represent the entities and relations in a given temporal knowledge graph (TKG) as low-dimensional vectors (i.e., embeddings), which preserve both semantic information and temporal dynamics of the factual information. In this paper, we posit that the intrinsic difficulty of existing TKGE methods lies in the lack of information in KG snapshots with timestamps, each of which contains the facts that co-occur at a specific timestamp. To address this challenge, we propose a novel self-supervised TKGE approach, THOR (Three-tower grapH cOnvolution netwoRks (GCNs)), which extracts latent knowledge from TKGs by jointly leveraging both temporal and atemporal dependencies between entities and the structural dependency between relations. THOR learns the embeddings of entities and relations, obtained from three-tower GCNs, via the following two objectives: (1) to maximize the likelihood of the facts in a TKG; (2) to address the lack of information in a TKG based on auxiliary supervision signals of each entity. Our experiments on three real-world datasets demonstrate that THOR significantly outperforms 13 competitors in terms of TKG completion tasks. THOR yields up to 9.37% higher accuracy, compared to the best competitor.