LGAIMay 21, 2022

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

arXiv:2205.10621v215 citationsh-index: 30
Originality Incremental advance
AI Analysis

This work addresses the challenge of few-shot learning for temporal knowledge graphs, which is important for applications requiring temporal reasoning, but it is incremental as it extends existing static KG methods to the temporal domain.

The paper tackles the problem of one-shot relational learning for temporal knowledge graphs (TKGs), which had been understudied compared to static knowledge graphs, by extending interpolated and extrapolated link prediction tasks to this setting and proposing new benchmark datasets. The result is a model that achieves superior performance on all datasets in both TKG link prediction tasks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes