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 issue of distribution shifts is emerging as a critical concern in graph representation
learning. From the perspective of invariant learning and stable learning, a recently well …

Abstract Out-of-distribution (OOD) learning deals with scenarios in which training and test
data follow different distributions. Although general OOD problems have been intensively …

Abstract Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by
learning the correlation between the input graphs and labels. However, by presenting a …

Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities
by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to …

Rationale is defined as a subset of input features that best explains or supports the
prediction by machine learning models. Rationale identification has improved the …

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 …

Dynamic graph neural networks (DyGNNs) currently struggle with handling distribution shifts
that are inherent in dynamic graphs. Existing work on DyGNNs with out-of-distribution …

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-
temporal patterns on dynamic graphs. However, existing works fail to generalize under …

Most existing deep learning models are trained based on the closed-world assumption,
where the test data is assumed to be drawn iid from the same distribution as the training …