Geometric Relational Embeddings: A Survey
It provides a comprehensive review for researchers in AI and machine learning, but it is incremental as it synthesizes existing methods without introducing new techniques.
This paper surveys geometric relational embeddings, which map relational data into geometric objects to combine machine learning with structured reasoning, addressing tasks like knowledge graph completion and logical query answering.
Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions. Their preservation of relational structures and their appealing properties and interpretability have led to their uptake for tasks such as knowledge graph completion, ontology and hierarchy reasoning, logical query answering, and hierarchical multi-label classification. We survey methods that underly geometric relational embeddings and categorize them based on (i) the embedding geometries that are used to represent the data; and (ii) the relational reasoning tasks that they aim to improve. We identify the desired properties (i.e., inductive biases) of each kind of embedding and discuss some potential future work.