Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-
dimensional spaces according to specific tasks. Up to now, there have been several surveys …

Advancements in neural machinery have led to a wide range of algorithmic solutions for
molecular property prediction. Two classes of models in particular have yielded promising …

This paper studies unsupervised/self-supervised whole-graph representation learning,
which is critical in many tasks such as molecule properties prediction in drug and material …

Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph
analysis tasks such as node classification and link prediction. However, important …

Graph neural networks (GNNs) have become the defacto standard for representation
learning on graphs, which derive effective node representations by recursively aggregating …

In recent years, graph neural networks (GNNs) have become the de facto tool for performing
machine learning tasks on graphs. Most GNNs belong to the family of message passing …

Graph kernels are historically the most widely-used technique for graph classification tasks.
However, these methods suffer from limited performance because of the hand-crafted …

Motivation Graphs or networks are widely utilized to model the interactions between different
entities (eg proteins, drugs, etc.) for biomedical applications. Predicting potential …

Graph kernels have attracted a lot of attention during the last decade, and have evolved into
a rapidly develo** branch of learning on structured data. During the past 20 years, the …

Pre-training Graph Neural Networks (GNN) via self-supervised contrastive learning has
recently drawn lots of attention. However, most existing works focus on node-level …