Work

A Shift in Perspective on Causality in Domain Generalization

Year: 2025

Type: preprint

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/.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2508.12798

Authors: Machlanski, Damian, Riley, Stephanie, Moroshko, Edward, Butler, Kurt, Dimitrakopoulos, Panagiotis, Melistas, Thomas, Chanchal, Akchunya, McDonagh, Steven, Silva, Ricardo, Tsaftaris, Sotirios A.

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: UK Research and Innovation, Engineering and Physical Sciences Research Council

Awards: Causality in Healthcare AI Hub, G6695034375

OpenAlex ID: W4414490293

Cites:

Cited by:

Related to: