Machine learning workflow enables faster, more reliable organic crystal structure prediction

Prediction of crystal structures of organic molecules is a critical task in many industries, especially in pharmaceuticals ...

Molecules bend, properties change: How nanographene transforms through oxidation

Graphene and its molecular fragments, known as nanographenes, are key materials for next-generation organic electronics due ...
IEEE

Enhancing Graph Structure Learning via Motif-Driven Hypergraph Construction

Abstract: Graph neural networks (GNNs), as a cutting-edge technology in deep learning, perform particularly well in various tasks that process graph structure data. However, their foundation on ...
IEEE

Graph Contrastive Learning for Fusion of Graph Structure and Attribute Information

Abstract: Graph Contrastive Learning (GCL) plays a crucial role in multimedia applications due to its effectiveness in analyzing graph-structured data. Existing GCL methods focus on maximizing the ...