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 …

Invariant graph representation learning aims to learn the invariance among data from
different environments for out-of-distribution generalization on graphs. As the graph …

Graph representation learning has shown effectiveness when testing and training graph
data come from the same distribution, but most existing approaches fail to generalize under …

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 …

There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so
that research on out-of-distribution (OOD) generalization comes into the spotlight …

In general, graph representation learning methods assume that the train and test data come
from the same distribution. In this work we consider an underexplored area of an otherwise …

Graph Neural Networks (GNNs) have achieved remarkable success in various domains but
most of them are developed under the in-distribution assumption. Under out-of-distribution …

Graph contrastive learning (GCL) is a promising direction toward alleviating the label
dependence, poor generalization and weak robustness of graph neural networks, learning …

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

Despite the remarkable success of graph neural networks (GNNs) for graph representation
learning, they are generally built on the (unreliable) iid assumption across training and …