Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
Abstract
The concern of overconfident mis-predictions under distributional shift demands extensive reliability research on Graph Neural Networks used in critical tasks in drug discovery. Here we first introduce CardioTox, a real-world benchmark on drug cardio-toxicity to facilitate such efforts. Our exploratory study shows overconfident mis-predictions are often distant from training data. That leads us to develop distance-aware GNNs: GNN-SNGP. Through evaluation on CardioTox and three established benchmarks, we demonstrate GNN-SNGP's effectiveness in increasing distance-awareness, reducing overconfident mis-predictions and making better calibrated predictions without sacrificing accuracy performance. Our ablation study further reveals the representation learned by GNN-SNGP improves distance-preservation over its base architecture and is one major factor for improvements.
Keywords
Cite
@article{arxiv.2111.12951,
title = {Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift},
author = {Kehang Han and Balaji Lakshminarayanan and Jeremiah Liu},
journal= {arXiv preprint arXiv:2111.12951},
year = {2021}
}
Comments
5 page main body, 5 page appendix. Accepted by NeurIPS DistShift Workshop 2021