# Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift

arXiv: https://arxiv.org/abs/2111.12951 · HTML: https://mlsanity.com/paper/2111.12951/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 21 of 21)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [Molecular Graph Convolutions: Moving Beyond Fingerprints](https://mlsanity.com/paper/1603.00856/) (2016)
- [i-RevNet: Deep Invertible Networks](https://mlsanity.com/paper/1802.07088/) (2018)
- [On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty](https://mlsanity.com/paper/2102.11409/) (2021)
- [Uncertainty Quantification Using Neural Networks for Molecular Property Prediction](https://mlsanity.com/paper/2005.10036/) (2020)
- [Reliable Graph Neural Networks via Robust Aggregation](https://mlsanity.com/paper/2010.15651/) (2020)
- [Machine learning on DNA-encoded libraries: A new paradigm for hit-finding](https://mlsanity.com/paper/2002.02530/) (2020)
- [Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks](https://mlsanity.com/paper/2009.10235/) (2020)
- [A benchmark study on reliable molecular supervised learning via Bayesian learning](https://mlsanity.com/paper/2006.07021/) (2020)

## Built on by (most cited first, 22 of 22)

- [Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2202.05441/) (2022)
- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness](https://mlsanity.com/paper/2205.00403/) (2022)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection](https://mlsanity.com/paper/2205.10014/) (2022)
- [Conformal Drug Property Prediction with Density Estimation under Covariate Shift](https://mlsanity.com/paper/2310.12033/) (2023)
- [Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges](https://mlsanity.com/paper/2203.12852/) (2022)
- [Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack](https://mlsanity.com/paper/2202.07114/) (2022)
- [Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS](https://mlsanity.com/paper/2212.01574/) (2022)
- [Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transport](https://mlsanity.com/paper/2202.06208/) (2022)
- [Kernel Regression with Infinite-Width Neural Networks on Millions of Examples](https://mlsanity.com/paper/2303.05420/) (2023)
- [DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training](https://mlsanity.com/paper/2405.05231/) (2024)
- [Backdoor Graph Condensation](https://mlsanity.com/paper/2407.11025/) (2024)
- [Morse Neural Networks for Uncertainty Quantification](https://mlsanity.com/paper/2307.00667/) (2023)
- [QDC: Quantum Diffusion Convolution Kernels on Graphs](https://mlsanity.com/paper/2307.11234/) (2023)
- [Graph-Guided Textual Explanation Generation Framework](https://mlsanity.com/paper/2412.12318/) (2024)
- [Achieving Well-Informed Decision-Making in Drug Discovery: A Comprehensive Calibration Study using Neural Network-Based Structure-Activity Models](https://mlsanity.com/paper/2407.14185/) (2024)
- [Residual and Attentional Architectures for Vector-Symbols](https://mlsanity.com/paper/2207.08953/) (2022)
- [Conditional Shift-Robust Conformal Prediction for Graph Neural Network](https://mlsanity.com/paper/2405.11968/) (2024)
- [RoCP-GNN: Robust Conformal Prediction for Graph Neural Networks in Node-Classification](https://mlsanity.com/paper/2408.13825/) (2024)
- [Self-Supervised Learning for Graph-Structured Data in Healthcare Applications: A Comprehensive Review](https://mlsanity.com/paper/2412.05312/) (2024)
- [Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Models](https://mlsanity.com/paper/2509.19588/) (2025)

## Abstract (arXiv)

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.