Why Isn't Relational Learning Taking Over the World?
This is a foundational critique for AI researchers and practitioners, highlighting a gap between common data formats and current machine learning methods, but it is incremental as it builds on existing relational learning concepts.
The paper addresses why relational learning, which models entities and their relations, has not become dominant in AI despite the prevalence of relational data in real-world applications like spreadsheets and databases, and outlines necessary steps to increase its prominence.
Artificial intelligence seems to be taking over the world with systems that model pixels, words, and phonemes. The world is arguably made up, not of pixels, words, and phonemes but of entities (objects, things, including events) with properties and relations among them. Surely we should model these, not the perception or description of them. You might suspect that concentrating on modeling words and pixels is because all of the (valuable) data in the world is in terms of text and images. If you look into almost any company you will find their most valuable data is in spreadsheets, databases and other relational formats. These are not the form that are studied in introductory machine learning, but are full of product numbers, student numbers, transaction numbers and other identifiers that can't be interpreted naively as numbers. The field that studies this sort of data has various names including relational learning, statistical relational AI, and many others. This paper explains why relational learning is not taking over the world -- except in a few cases with restricted relations -- and what needs to be done to bring it to it's rightful prominence.