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 …

Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input
graph's features--rationale--which guides the model prediction. Unfortunately, the leading …

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) …

We study how neural networks trained by gradient descent extrapolate, ie, what they learn
outside the support of the training distribution. Previous works report mixed empirical results …

Abstract Invariant Risk Minimization (IRM) is an emerging invariant feature extracting
technique to help generalization with distributional shift. However, we find that there exists a …

Attention module does not always help deep models learn causal features that are robust in
any confounding context, eg, a foreground object feature is invariant to different …

Despite remarkable success in a variety of applications, it is well-known that deep learning
can fail catastrophically when presented with out-of-distribution data. Toward addressing …

Generalization to out-of-distribution (OOD) data is one of the central problems in modern
machine learning. Recently, there is a surge of attempts to propose algorithms that mainly …

Generalization under distributional shift is an open challenge for machine learning. Invariant
Risk Minimization (IRM) is a promising framework to tackle this issue by extracting invariant …