mlsanityData to 14 Oct 2026

Why Isn't Relational Learning Taking Over the World?

arXiv 2507.13558 ↗First posted 17 Jul 2025cs.AI cs.DB cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 59 references that are in the map. First posted on arXiv 17 Jul 2025.

Builds on

13 of 59 references.

References · 13

  1. 2017Graph Attention Networkscited by 8,923
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  5. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 343
  6. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 96
  7. 2013A Semantic Matching Energy Function for Learning with Multi-relational Datacited by 61
  8. 2016On the representation and embedding of knowledge bases beyond binary relationscited by 55
  9. 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarkscited by 53
  10. 2014Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inferencecited by 23
  11. 2025Unreflected Use of Tabular Data Repositories Can Undermine Research Qualitycited by 9
  12. 2024Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterizationcited by 7
1 more
  1. 2017Comparing Aggregators for Relational Probabilistic Modelscited by 1

Built on by

Not cited yet.