Temporal Relevance for Representing Learning over Temporal Knowledge Graphs

Tracking #: 3557-4771

This paper is currently under review
Bowen Song
Kossi Amouzouvi
Chengjin Xu
Maocai Wang
Jens Lehmann
Sahar Vahdati

Responsible editor: 
Armin Haller

Submission type: 
Full Paper
Representation learning for link prediction is one of the leading approaches to deal with incompleteness problem of real world knowledge graphs. Such methods are often called knowledge graph embedding models which represent entities and relationships in knowledge graphs in continuous vector spaces. By doing this, semantic relationships and patterns can be captured in the form of compact vectors. In temporal knowledge graphs, the connection of temporal and relational information is crucial for representing facts accurately. Relations provide the semantic context for facts, while timestamps indicate their temporal validity. However, existing embedding models often overlook the intricate interplay between relational and temporal parts of the facts in temporal knowledge graphs. These models tend to focus on effectively representing individual components, consequently capturing only a fraction of the overall knowledge. Additionally, some relations in temporal facts are time-insensitive, while others are highly time-dependent. This complexity reduces the ability of temporal knowledge graph embedding models in accurately capturing these characteristics. To address these challenges, we propose a novel embedding model based on temporal relevance. This model operates within a complex space with real and imaginary parts to effectively embed temporal knowledge graphs. Specifically, the real part of the embeddings of our proposed model captures the semantic characteristics of facts by considering the importance of temporal information and relational information associated with each fact. Simultaneously, the imaginary part of the embeddings learns the connections between diverse elements, without predefined weights. Our approach is evaluated through extensive experiments on the link prediction task, where it majorly outperforms state-of-the-art models. The proposed model also demonstrates remarkable effectiveness in capturing the complexities of temporal knowledge graphs.
Full PDF Version: 
Under Review