Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks

S Chandra Mouli · Bruno Ribeiro

Keywords: [ geometric deep learning ]

[ Abstract ]
[ Visit Poster at Spot G3 in Virtual World ] [ OpenReview
Thu 28 Apr 10:30 a.m. PDT — 12:30 p.m. PDT
Oral presentation: Oral 3: Learning from distribution shift
Wed 27 Apr 9 a.m. PDT — 10:30 a.m. PDT

Abstract: Generalizing from observed to new related environments (out-of-distribution) is central to the reliability of classifiers. However, most classifiers fail to predict label $Y$ from input $X$ when the change in environment is due a (stochastic) input transformation $T^\text{te} \circ X'$ not observed in training, as in training we observe $T^\text{tr} \circ X'$, where $X'$ is a hidden variable. This work argues that when the transformations in train $T^\text{tr}$ and test $T^\text{te}$ are (arbitrary) symmetry transformations induced by a collection of known $m$ equivalence relations, the task of finding a robust OOD classifier can be defined as finding the simplest causal model that defines a causal connection between the target labels and the symmetry transformations that are associated with label changes. We then propose a new learning paradigm, asymmetry learning, that identifies which symmetries the classifier must break in order to correctly predict $Y$ in both train and test. Asymmetry learning performs a causal model search that, under certain identifiability conditions, finds classifiers that perform equally well in-distribution and out-of-distribution. Finally, we show how to learn counterfactually-invariant representations with asymmetry learning in two physics tasks.

Chat is not available.