Uncertainty quantification for molecular property predictions with graph neural architecture search
Shengli Jiang, Shiyi Qin, Reid C. Van Lehn, Prasanna Balaprakash, Victor M. Zavala
Abstract
AutoGNNUQ employs neural architecture search to enhance uncertainty quantification for molecular property prediction via graph neural networks.
Topics & Concepts
Computer scienceArchitectureArtificial neural networkProperty (philosophy)GraphArtificial intelligenceMachine learningTheoretical computer scienceArtPhilosophyEpistemologyVisual artsComputational Drug Discovery MethodsMachine Learning in Materials ScienceProtein Structure and Dynamics