Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization. (arXiv:2206.07837v1 [cs.LG])

Web: http://arxiv.org/abs/2206.07837

Real-world data collected from multiple domains can have multiple, distinct
distribution shifts over multiple attributes. However, state-of-the art
advances in domain generalization (DG) algorithms focus only on specific shifts
over a single attribute. We introduce datasets with multi-attribute
distribution shifts and find that existing DG algorithms fail to generalize. To
explain this, we use causal graphs to characterize the different types of
shifts based on the relationship between spurious attributes and the
classification label. Each multi-attribute causal graph entails different …

arxiv data distribution lg modeling process