Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information

TL;DR

This paper introduces a meta-learning approach for few-shot inductive link prediction on temporal knowledge graphs, effectively handling unseen entities by leveraging concept-aware information and new datasets.

Contribution

It proposes a novel few-shot out-of-graph link prediction task for TKGs, along with a concept-aware model and new datasets, advancing inductive reasoning in temporal KGs.

Findings

Our model outperforms baselines on three new datasets.

Concept-aware information significantly improves prediction accuracy.

The approach effectively models unseen entities in TKGs.

Abstract

Knowledge graph completion (KGC) aims to predict the missing links among knowledge graph (KG) entities. Though various methods have been developed for KGC, most of them can only deal with the KG entities seen in the training set and cannot perform well in predicting links concerning novel entities in the test set. Similar problem exists in temporal knowledge graphs (TKGs), and no previous temporal knowledge graph completion (TKGC) method is developed for modeling newly-emerged entities. Compared to KGs, TKGs require temporal reasoning techniques for modeling, which naturally increases the difficulty in dealing with novel, yet unseen entities. In this work, we focus on the inductive learning of unseen entities' representations on TKGs. We propose a few-shot out-of-graph (OOG) link prediction task for TKGs, where we predict the missing entities from the links concerning unseen entities by employing a meta-learning framework and utilizing the meta-information provided by only few edges associated with each unseen entity. We construct three new datasets for TKG few-shot OOG link prediction, and we propose a model that mines the concept-aware information among entities. Experimental results show that our model achieves superior performance on all three datasets and our concept-aware modeling component demonstrates a strong effect.