A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications

arXiv:2403.00485v1 Announce Type: new
Abstract: Geometric graph is a special kind of graph with geometric features, which is vital to model many scientific problems. Unlike generic graphs, geometric graphs often exhibit physical symmetries of translations, rotations, and reflections, making them ineffectively processed by current Graph Neural Networks (GNNs). To tackle this issue, researchers proposed a variety of Geometric Graph Neural Networks equipped with invariant/equivariant properties to better characterize the geometry and topology of geometric graphs. Given the current progress in …

abstract applications arxiv cs.lg current data features gnns graph graph neural networks graphs kind making networks neural networks reflections survey them type vital