A Shift in Perspective on Causality in Domain Generalization
It addresses theoretical inconsistencies in causality for domain generalization, which is important for researchers in robust AI, but appears incremental.
The paper revisits the role of causality in domain generalization, reconciling contradictions in the literature and advocating for a more nuanced theory, with an interactive demo provided.
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/.