On the Expressive Power of Graph Neural Networks

arXiv:2401.01626v2 Announce Type: replace
Abstract: The study of Graph Neural Networks has received considerable interest in the past few years. By extending deep learning to graph-structured data, GNNs can solve a diverse set of tasks in fields including social science, chemistry, and medicine. The development of GNN architectures has largely been focused on improving empirical performance on tasks like node or graph classification. However, a line of recent work has instead sought to find GNN architectures that have desirable theoretical …

abstract architectures arxiv chemistry cs.ai cs.lg data deep learning development diverse fields gnn gnns graph graph neural networks medicine networks neural networks power science set social social science solve structured data study tasks type