Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction

TL;DR

This paper introduces a novel approach for one-shot relation learning in temporal knowledge graphs, extending static KG methods to handle rich temporal data and reasoning tasks.

Contribution

It proposes a new model and four large-scale benchmarks for one-shot relation learning in TKGs, addressing a gap in temporal reasoning research.

Findings

Our model outperforms baselines on all datasets.

Effective in interpolated and extrapolated link prediction tasks.

Provides new benchmarks for future TKG research.

Abstract

Few-shot relational learning for static knowledge graphs (KGs) has drawn greater interest in recent years, while few-shot learning for temporal knowledge graphs (TKGs) has hardly been studied. Compared to KGs, TKGs contain rich temporal information, thus requiring temporal reasoning techniques for modeling. This poses a greater challenge in learning few-shot relations in the temporal context. In this paper, we follow the previous work that focuses on few-shot relational learning on static KGs and extend two fundamental TKG reasoning tasks, i.e., interpolated and extrapolated link prediction, to the one-shot setting. We propose four new large-scale benchmark datasets and develop a TKG reasoning model for learning one-shot relations in TKGs. Experimental results show that our model can achieve superior performance on all datasets in both TKG link prediction tasks.