Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs

TL;DR

This survey reviews methods for knowledge extrapolation in knowledge graphs, focusing on handling unseen entities and relations, and provides a taxonomy, benchmarks, and future research directions.

Contribution

It unifies various knowledge extrapolation methods under a common taxonomy and offers comprehensive benchmarks and analysis.

Findings

Summarizes existing knowledge extrapolation techniques.

Provides a unified taxonomy for these methods.

Includes benchmarks and comparative analysis.

Abstract

Knowledge graphs (KGs) have become valuable knowledge resources in various applications, and knowledge graph embedding (KGE) methods have garnered increasing attention in recent years. However, conventional KGE methods still face challenges when it comes to handling unseen entities or relations during model testing. To address this issue, much effort has been devoted to various fields of KGs. In this paper, we use a set of general terminologies to unify these methods and refer to them collectively as Knowledge Extrapolation. We comprehensively summarize these methods, classified by our proposed taxonomy, and describe their interrelationships. Additionally, we introduce benchmarks and provide comparisons of these methods based on aspects that are not captured by the taxonomy. Finally, we suggest potential directions for future research.