A Shift in Perspective on Causality in Domain Generalization
By: Damian Machlanski , Stephanie Riley , Edward Moroshko and more
Potential Business Impact:
Makes AI learn better from different situations.
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/.
Similar Papers
Effect of Domain Generalization Techniques in Low Resource Systems
Computation and Language
Makes computer language learning work better everywhere.
Generalizing to Unseen Disaster Events: A Causal View
Computation and Language
Helps social media spot disaster news better.
CAMO: Causality-Guided Adversarial Multimodal Domain Generalization for Crisis Classification
Machine Learning (CS)
Helps computers understand disaster messages better.