Property prediction on molecular graphs is an important application of Graph Neural
Networks (GNNs). Recently, unlabeled molecular data has become abundant, which …

Predicting molecular properties with data-driven methods has drawn much attention in
recent years. Particularly, Graph Neural Networks (GNNs) have demonstrated remarkable …

Molecular representation learning is crucial for the problem of molecular property prediction,
where graph neural networks (GNNs) serve as an effective solution due to their structure …

Molecular property prediction (eg, energy) is an essential problem in chemistry and biology.
Unfortunately, many supervised learning methods usually suffer from the problem of scarce …

Recent global events have emphasized the importance of accelerating the drug discovery
process. A way to deal with the issue is to use machine learning to increase the rate at which …

Many applications of machine learning require a model to make accurate pre-dictions on
test examples that are distributionally different from training ones, while task-specific labels …

Molecular graph representation learning has shown considerable strength in molecular
analysis and drug discovery. Due to the difficulty of obtaining molecular property labels, pre …

Attribute reconstruction is used to predict node or edge features in the pre-training of graph
neural networks. Given a large number of molecules, they learn to capture structural …

Molecule generation is central to a variety of applications. Current attention has been paid to
approaching the generation task as subgraph prediction and assembling. Nevertheless …

Designing accurate deep learning models for molecular property prediction plays an
increasingly essential role in drug and material discovery. Recently, due to the scarcity of …