Litcius/Paper detail

A general framework for quantifying aleatoric and epistemic uncertainty in graph neural networks

Sai Munikoti, Deepesh Agarwal, Laya Das, Balasubramaniam Natarajan

2022Neurocomputing19 citationsDOI

Topics & Concepts

Uncertainty quantificationComputer scienceFrequentist inferenceUncertainty analysisSensitivity analysisMachine learningBayesian probabilityMeasurement uncertaintyArtificial intelligenceProbabilistic logicMonte Carlo methodGraphPropagation of uncertaintyBayesian inferenceData miningAlgorithmMathematicsTheoretical computer scienceStatisticsSimulationAdvanced Graph Neural NetworksBayesian Modeling and Causal InferenceExplainable Artificial Intelligence (XAI)
A general framework for quantifying aleatoric and epistemic uncertainty in graph neural networks | Litcius