Why Isn't Relational Learning Taking Over the World?

TL;DR

Relational learning focuses on modeling entities and their relations, but it remains underutilized compared to pixel and text modeling, due to challenges and limited scope in current applications.

Contribution

The paper analyzes the reasons behind the limited adoption of relational learning and discusses what is needed to enhance its prominence in AI.

Findings

Relational learning is underused outside restricted cases.

Most valuable data is in relational formats like databases.

Significant work is needed to advance relational learning.

Abstract

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.