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 …

Abstract Machine learning algorithms typically assume that training and test examples are
drawn from the same distribution. However, distribution shift is a common problem in real …

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 …

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 …

Deep neural networks often rely on spurious correlations to make predictions, which hinders
generalization beyond training environments. For instance, models that associate cats with …

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 …

Machine learning systems are known to be sensitive to spurious correlations between non-
essential features of the inputs (eg, background, texture, and secondary objects) and the …

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 …

Graph machine learning has been extensively studied in both academia and industry.
Although booming with a vast number of emerging methods and techniques, most of the …

Abstract Out-of-distribution (OOD) generalization is an important issue for Graph Neural
Networks (GNNs). Recent works employ different graph editions to generate augmented …