StATIK: Structure and Text for Inductive Knowledge Graph Completion

Elan Sopher Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Murali Annavaram, Aram Galstyan, Greg Ver Steeg

Abstract: Knowledge graphs (KGs) often represent knowledge bases that are incomplete. Machine learning models can alleviate this by helping automate graph completion. Recently, there has been growing interest in completing knowledge bases that are dynamic, where previously unseen entities may be added to the KG with many missing links. In this paper, we present \textbf{StATIK}--\textbf{St}ructure \textbf{A}nd \textbf{T}ext for \textbf{I}nductive \textbf{K}nowledge Completion. \texttt{StATIK} uses Language Models to extract the semantic information from text descriptions, while using Message Passing Neural Networks to capture the structural information. \texttt{StATIK} achieves state of the art results on three challenging inductive baselines. We further analyze our hybrid model through detailed ablation studies.