The convenient access to copious multifaceted data has encouraged machine learning
researchers to reconsider correlation-based learning and embrace the opportunity of …

Deep graph learning has achieved remarkable progresses in both business and scientific
areas ranging from finance and e-commerce, to drug and advanced material discovery …

Combinatorial optimization is a well-established area in operations research and computer
science. Until recently, its methods have focused on solving problem instances in isolation …

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 …

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 …

This work studies the evaluation of explaining graph neural networks (GNNs), which is
crucial to the credibility of post-hoc explainability in practical usage. Conventional evaluation …

Molecule representation learning (MRL) has been extensively studied and current methods
have shown promising power for various tasks, eg, molecular property prediction and target …

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 …

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 …

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