Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs
This work organizes and reviews methods for improving generalization in knowledge graphs, which is incremental as it synthesizes existing research rather than introducing new techniques.
This survey addresses the problem of knowledge graph embedding methods struggling with unseen entities or relations by unifying and classifying existing approaches under the term 'Knowledge Extrapolation', providing a comprehensive summary, taxonomy, benchmarks, and future directions.
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.