A Shift in Perspective on Causality in Domain Generalization
Damian Machlanski, Stephanie Riley, Edward Moroshko, Kurt Butler, Panagiotis Dimitrakopoulos, Thomas Melistas, Akchunya Chanchal, Steven McDonagh, Ricardo Silva, Sotirios A. Tsaftaris
TL;DR
This paper reevaluates the role of causal modeling in domain generalization, highlighting nuanced perspectives and clarifying previous contradictions to better understand AI robustness across diverse environments.
Contribution
It offers a revised, nuanced theory of causality's influence on generalization and clarifies misconceptions in the current DG literature.
Findings
Reconciles conflicting views on causality in DG
Proposes a more nuanced understanding of causality's role
Provides an interactive demo for causal predictors
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/.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAI-based Problem Solving and Planning · Software Engineering Research