A Shift in Perspective on Causality in Domain Generalization

Damian Machlanski, Stephanie Riley, Edward Moroshko, Kurt Butler, Panagiotis Dimitrakopoulos +5 more
8/18/2025
cs.LGcs.AIcs.CV

No confident code implementation found for this paper.

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/.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Causal Framework to Unify Common Domain Generalization Approaches

89% match2023

Do causal predictors generalize better to new domains?

87% match1 repo172026

Causality-inspired Latent Feature Augmentation for Single Domain Generalization

85% match2024

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery

84% match2024

Emerging Synergies in Causality and Deep Generative Models: A Survey

84% match2023

Causality can systematically address the monsters under the bench(marks)

84% match2025

Cite this paper

@article{machlanski2025shift,
  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},
  year   = {2025},
  eprint = {2508.12798},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.12798v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.12798.svg)](https://codeofpaper.com/paper/2508.12798)

Discussion