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 …

As artificial intelligence (AI) rapidly approaches human-level performance in medical
imaging, it is crucial that it does not exacerbate or propagate healthcare disparities. Previous …

Deep classifiers are known to rely on spurious features—patterns which are correlated with
the target on the training data but not inherently relevant to the learning problem, such as the …

Different distribution shifts require different algorithmic and operational interventions.
Methodological research must be grounded by the specific shifts they address. Although …

Abstract Machine learning models have been found to learn shortcuts---unintended decision
rules that are unable to generalize---undermining models' reliability. Previous works address …

Existing long-tailed classification (LT) methods only focus on tackling the class-wise
imbalance that head classes have more samples than tail classes, but overlook the attribute …

Machine learning models often perform poorly on subgroups that are underrepresented in
the training data. Yet, little is understood on the variation in mechanisms that cause …

Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious
correlations and poor generalization on minority groups. The recent deep feature …

A major challenge to out-of-distribution generalization is reliance on spurious features—
patterns that are predictive of the class label in the training data distribution, but not causally …

Several studies have compared the in-distribution (ID) and out-of-distribution (OOD)
performance of models in computer vision and NLP. They report a frequent positive …