Graph factorizations constitute a fundamental area of graph theory in which complex networks are decomposed into subgraphs, or factors, that adhere to specific properties. These factorizations not ...

Nanoengineers at the University of California San Diego have developed new deep learning models that can accurately predict the properties of molecules and crystals. By enabling almost instantaneous ...

As an emerging technology in the field of artificial intelligence (AI), graph neural networks (GNNs) are deep learning models designed to process graph-structured data. Currently, GNNs are effective ...

A team of researchers at ETH Zurich are working on a novel approach to solving increasingly large graph problems. Large graphs are a basis of many problems in social sciences (e.g., studying human ...