Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction

7 Oct 2019Gabriele ScaliaColin A. GrambowBarbara PerniciYi-Pei LiWilliam H. Green

Advances in deep neural network (DNN) based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolution neural networks (GCNNs) reporting state-of-the-art performance for this task. However, some challenges remain and one of the most important that needs to be fully addressed concerns uncertainty quantification... (read more)

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper