AIAug 24, 2022

A Review of Knowledge Graph Completion

arXiv:2208.11652v191 citationsh-index: 21
Originality Synthesis-oriented
AI Analysis

This is an incremental review that synthesizes existing techniques for researchers and practitioners working with incomplete knowledge graphs.

The paper reviews methods for knowledge graph completion, focusing on predicting missing links to improve downstream task usability, and categorizes approaches into conventional independent triple processing and GNN-based methods that incorporate local neighborhood information.

Information extraction methods proved to be effective at triple extraction from structured or unstructured data. The organization of such triples in the form of (head entity, relation, tail entity) is called the construction of Knowledge Graphs (KGs). Most of the current knowledge graphs are incomplete. In order to use KGs in downstream tasks, it is desirable to predict missing links in KGs. Different approaches have been recently proposed for representation learning of KGs by embedding both entities and relations into a low-dimensional vector space aiming to predict unknown triples based on previously visited triples. According to how the triples will be treated independently or dependently, we divided the task of knowledge graph completion into conventional and graph neural network representation learning and we discuss them in more detail. In conventional approaches, each triple will be processed independently and in GNN-based approaches, triples also consider their local neighborhood. View Full-Text

Foundations

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

Your Notes