HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning
This work addresses the challenge of predicting dynamic facts in temporal knowledge graphs, which is important for applications like recommendation systems and event forecasting, but it is incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of Temporal Knowledge Graph (TKG) reasoning for predicting future facts by proposing HiSMatch, a model that matches queries to candidate entities based on historical structures and background knowledge, achieving up to 5.6% improvement in MRR over state-of-the-art baselines on six benchmark datasets.
A Temporal Knowledge Graph (TKG) is a sequence of KGs with respective timestamps, which adopts quadruples in the form of (\emph{subject}, \emph{relation}, \emph{object}, \emph{timestamp}) to describe dynamic facts. TKG reasoning has facilitated many real-world applications via answering such queries as (\emph{query entity}, \emph{query relation}, \emph{?}, \emph{future timestamp}) about future. This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps. In addition, recent KGs provide background knowledge of all the entities, which is also helpful for the matching. Thus, in this paper, we propose the \textbf{Hi}storical \textbf{S}tructure \textbf{Match}ing (\textbf{HiSMatch}) model. It applies two structure encoders to capture the semantic information contained in the historical structures of the query and candidate entities. Besides, it adopts another encoder to integrate the background knowledge into the model. TKG reasoning experiments on six benchmark datasets demonstrate the significant improvement of the proposed HiSMatch model, with up to 5.6\% performance improvement in MRR, compared to the state-of-the-art baselines.