Temporal Relevance for Representing Learning over Temporal Knowledge Graphs

Tracking #: 3699-4913

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 the temporal validity of facts. The importance of time is different for the semantics of different facts. Some relations in some temporal facts are time-insensitive, while others are highly time-dependent. However, existing embedding models often overlook the time sensitivity of different facts in temporal knowledge graphs. These models tend to focus on effectively representing connection between individual components of quadruples, consequently capturing only a fraction of the overall knowledge. Ignoring importance of temporal properties 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, which can effectively capture the time sensitivity of semantics and better represent facts. This model operates within a complex space with real and imaginary parts to effectively embed temporal knowledge graphs. Specifically, the real part of the final embedding of our proposed model captures semantic characteristic with temporal sensitivity by learning the relational information and temporal information through transformation and attention mechanism. Simultaneously, the imaginary part of the embeddings learns the connections between different elements in the fact 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