A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledge

TL;DR

This survey reviews recent methods for few-shot knowledge graph completion, emphasizing the integration of structural and commonsense knowledge to address data scarcity in long-tail and new relations.

Contribution

It systematically categorizes existing FKGC approaches, discusses challenges, and highlights applications and future directions in the field.

Findings

Comprehensive categorization of FKGC methods

Identification of key challenges in FKGC

Discussion of applications across domains

Abstract

Knowledge graphs (KG) have served as the key component of various natural language processing applications. Commonsense knowledge graphs (CKG) are a special type of KG, where entities and relations are composed of free-form text. However, previous works in KG completion and CKG completion suffer from long-tail relations and newly-added relations which do not have many know triples for training. In light of this, few-shot KG completion (FKGC), which requires the strengths of graph representation learning and few-shot learning, has been proposed to challenge the problem of limited annotated data. In this paper, we comprehensively survey previous attempts on such tasks in the form of a series of methods and applications. Specifically, we first introduce FKGC challenges, commonly used KGs, and CKGs. Then we systematically categorize and summarize existing works in terms of the type of KGs and the methods. Finally, we present applications of FKGC models on prediction tasks in different areas and share our thoughts on future research directions of FKGC.