Knowledge graphs are collections of real-world triples, where each triple or fact (h, r, t) in KGs represents some relation r between a head entity h and a tail entity t. KGs can thus be formalized as directed multi-relational graphs, where nodes correspond to entities and edges linking the nodes encode various kinds of relationships.

University of Michigan - Ann Arbor

A survey of embedding models of entities and relationships for knowledge graph completion

because knowledge graphs are typically incomplete, it is useful to perform knowledge graph completion or link prediction, i.e. predict whether a relationship not in the knowledge graph is likely to be true.

When to use the Knowledge Graphs


This paper serves as a comprehensive survey of embedding models of entities and relationships for knowledge graph completion, summarizing up-to-date experimental results on standard benchmark datasets and pointing out potential future research directions.

Purpose of this survey

Objects in the Knowledge graphs

Other KG Completion Model:

The Path Ranking Algorithm (PRA) is a random walk inference technique which was proposed to predict a new relationship between two entities in KGs

This model is able to estimate the probability of an unseen triple as a combination of weighted random walks that follow different paths linking the head entity and tail entity in the KG

Specific models

(i) Combining logical rules which contain rich background information and KG triples in a unified KG completion framework, e.g. jointly embedding KGs and logical rules

 (ii) Recent embedding models for KG completion hold a closed-world assumption where the KGs are fixed (i.e. new entities might not be added easily), therefore it would be worth exploring open-world KG completion models to connect unseen entities to the existing KGs. 

(iii) Investigating efficient approaches which can be applied to large-scale KGs of millions of entities and relation

Learn Before

Related