Knowledge Graph Embeddings and Explainable AI

TL;DR

This paper introduces knowledge graph embeddings, discusses their generation and evaluation, reviews state-of-the-art methods, and explores explainability techniques for AI predictions based on these embeddings.

Contribution

It provides a comprehensive overview of knowledge graph embeddings, including recent approaches and methods for enhancing explainability in AI models.

Findings

Summarizes current state-of-the-art in knowledge graph embeddings

Discusses methods for explaining AI predictions using embeddings

Highlights challenges and future directions in explainable knowledge graph embeddings

Abstract

Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces. In this chapter, we introduce the reader to the concept of knowledge graph embeddings by explaining what they are, how they can be generated and how they can be evaluated. We summarize the state-of-the-art in this field by describing the approaches that have been introduced to represent knowledge in the vector space. In relation to knowledge representation, we consider the problem of explainability, and discuss models and methods for explaining predictions obtained via knowledge graph embeddings.