A Shift in Perspective on Causality in Domain Generalization
Machine Learning
2025-08-19 v1 Artificial Intelligence
Computer Vision and Pattern Recognition
Abstract
The promise that causal modelling can lead to robust AI generalization has been challenged in recent work on domain generalization (DG) benchmarks. We revisit the claims of the causality and DG literature, reconciling apparent contradictions and advocating for a more nuanced theory of the role of causality in generalization. We also provide an interactive demo at https://chai-uk.github.io/ukairs25-causal-predictors/.
Keywords
Cite
@article{arxiv.2508.12798,
title = {A Shift in Perspective on Causality in Domain Generalization},
author = {Damian Machlanski and Stephanie Riley and Edward Moroshko and Kurt Butler and Panagiotis Dimitrakopoulos and Thomas Melistas and Akchunya Chanchal and Steven McDonagh and Ricardo Silva and Sotirios A. Tsaftaris},
journal= {arXiv preprint arXiv:2508.12798},
year = {2025}
}
Comments
2 pages, 1 figure, to be presented at the UK AI Research Symposium (UKAIRS) 2025