Knowledge Graph Embeddings and Explainable AI
This is an incremental overview for researchers and practitioners in AI and knowledge representation, focusing on explainability in a specific domain.
The chapter introduces knowledge graph embeddings as a method for representing entities and relationships in vector spaces, summarizing state-of-the-art approaches and discussing models for explaining predictions from these embeddings.
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.