mlsanityData to 7 Oct 2026

Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift

arXiv 2111.12951 ↗First posted 25 Nov 2021cs.LG cs.AIcited by 22

Not on the map. Why?

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.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 25 Nov 2021.

Builds on

21 of 32 references.

References · 21

  1. 2017Graph Attention Networkscited by 8,854
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  7. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  8. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  9. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  10. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  11. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  12. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
9 more
  1. 2018Graph networks as learnable physics engines for inference and controlcited by 242
  2. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  3. 2018i-RevNet: Deep Invertible Networkscited by 137
  4. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
  5. 2020Uncertainty Quantification Using Neural Networks for Molecular Property Predictioncited by 66
  6. 2020Reliable Graph Neural Networks via Robust Aggregationcited by 43
  7. 2020Machine learning on DNA-encoded libraries: A new paradigm for hit-findingcited by 15
  8. 2020Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attackscited by 15
  9. 2020A benchmark study on reliable molecular supervised learning via Bayesian learningcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 9; 2023: 4; 2024: 8; 2025: 1.

22 papers.

Sort:

  1. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  2. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  3. 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
  4. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  5. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  6. 2023Conformal Drug Property Prediction with Density Estimation under Covariate Shiftcited by 13
  7. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  8. 2022Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attackcited by 10
  9. 2022Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUScited by 10
  10. 2022Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transportcited by 9
  11. 2023Kernel Regression with Infinite-Width Neural Networks on Millions of Examplescited by 9
  12. 2024DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Trainingcited by 5
10 more
  1. 2024Backdoor Graph Condensationcited by 5
  2. 2023Morse Neural Networks for Uncertainty Quantificationcited by 4
  3. 2023QDC: Quantum Diffusion Convolution Kernels on Graphscited by 4
  4. 2024Graph-Guided Textual Explanation Generation Frameworkcited by 3
  5. 2024Achieving Well-Informed Decision-Making in Drug Discovery: A Comprehensive Calibration Study using Neural Network-Based Structure-Activity Modelscited by 2
  6. 2022Residual and Attentional Architectures for Vector-Symbolscited by 1
  7. 2024Conditional Shift-Robust Conformal Prediction for Graph Neural Networkcited by 1
  8. 2024RoCP-GNN: Robust Conformal Prediction for Graph Neural Networks in Node-Classificationcited by 0
  9. 2024Self-Supervised Learning for Graph-Structured Data in Healthcare Applications: A Comprehensive Reviewcited by 0
  10. 2025Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Modelscited by 0