Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
arXiv:2111.12951
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.
5 page main body, 5 page appendix. Accepted by NeurIPS DistShift Workshop 2021
References in corpus (6)
- Interaction Networks for Learning about Objects, Relations and Physics
- Uncertainty Estimation Using a Single Deep Deterministic Neural Network
- Machine learning on DNA-encoded libraries: A new paradigm for hit-finding
- On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
- Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks
- A benchmark study on reliable molecular supervised learning via Bayesian learning