Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

The invariance principle from causality is at the heart of notable approaches such as
invariant risk minimization (IRM) that seek to address out-of-distribution (OOD) …

Despite recent success in using the invariance principle for out-of-distribution (OOD)
generalization on Euclidean data (eg, images), studies on graph data are still limited …

Recently, there has been a growing surge of interest in enabling machine learning systems
to generalize well to Out-of-Distribution (OOD) data. Most efforts are devoted to advancing …

Several existing works study either adversarial or natural distributional robustness of deep
neural networks separately. In practice, however, models need to enjoy both types of …

Since the introduction of deep learning, a wide scope of representation properties, such as
decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have …

Abstract Domain generalization aims at performing well on unseen test environments with
data from a limited number of training environments. Despite a proliferation of proposed …

Abstract Domain generalization asks for models trained over a set of training environments
to perform well in unseen test environments. Recently, a series of algorithms such as …

This work discusses how to achieve worst-case Out-Of-Distribution (OOD) generalization for
a variety of distributions based on a relatively small labeling cost. The problem has broad …