mlsanityData to 7 Oct 2026

Uncertainty in Graph Neural Networks: A Survey

arXiv 2403.07185 ↗First posted 11 Mar 2024cs.LG stat.MLcited by 20

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have been extensively used in various real-world applications. However, the predictive uncertainty of GNNs stemming from diverse sources such as inherent randomness in data and model training errors can lead to unstable and erroneous predictions. Therefore, identifying, quantifying, and utilizing uncertainty are essential to enhance the performance of the model for the downstream tasks as well as the reliability of the GNN predictions. This survey aims to provide a comprehensive overview of the GNNs from the perspective of uncertainty with an emphasis on its integration in graph learning. We compare and summarize existing graph uncertainty theory and methods, alongside the corresponding downstream tasks. Thereby, we bridge the gap between theory and practice, meanwhile connecting different GNN communities. Moreover, our work provides valuable insights into promising directions in this field.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 76 of its 103 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

76 of 103 references.

References · 76

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  10. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  11. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  12. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
38 more
  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  3. 2020A Survey of Deep Active Learningcited by 547
  4. 2022Conformal prediction beyond exchangeabilitycited by 348
  5. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  6. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  7. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 179
  8. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  9. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  10. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  11. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  12. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  13. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
  14. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 88
  15. 2019Variational Graph Recurrent Neural Networkscited by 86
  16. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  17. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  18. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  19. 2023Uncertainty Quantification over Graph with Conformalized Graph Neural Networkscited by 79
  20. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  21. 2019Certifiable Robustness to Graph Perturbationscited by 62
  22. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 62
  23. 2017Active Learning for Graph Embeddingcited by 53
  24. 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
  25. 2021Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphscited by 49
  26. 2021Quantifying Uncertainty in Deep Spatiotemporal Forecastingcited by 48
  27. 2022What Makes Graph Neural Networks Miscalibrated?cited by 39
  28. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  29. 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
  30. 2021GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networkscited by 35
  31. 2023Topology-Aware Uncertainty for Image Segmentationcited by 32
  32. 2022PyGOD: A Python Library for Graph Outlier Detectioncited by 31
  33. 2022Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networkscited by 29
  34. 2023Learning on Graphs with Out-of-Distribution Nodescited by 29
  35. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 29
  36. 2022Distribution Free Prediction Sets for Node Classificationcited by 28
  37. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  38. 2024ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentationcited by 25

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 10; 2026: 5.

20 papers.

Sort:

By area:

  1. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  2. 2025Uncertainty-Aware Graph Structure Learningcited by 4
  3. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  4. 2025Topology-Aware Conformal Prediction for Stream Networkscited by 3
  5. 2026Random-Set Graph Neural Networkscited by 3
  6. 2025Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimizationcited by 2
  7. 2025Credal Graph Neural Networkscited by 2
  8. 2024Conditional Shift-Robust Conformal Prediction for Graph Neural Networkcited by 1
  9. 2025Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Taskscited by 1
  10. 2024Node Classification With Integrated Reject Optioncited by 0
  11. 2024REGE: A Method for Incorporating Uncertainty in Graph Embeddingscited by 0
  12. 2025CRC-SGAD: Conformal Risk Control for Supervised Graph Anomaly Detectioncited by 0
8 more
  1. 2025How Particle System Theory Enhances Hypergraph Message Passingcited by 0
  2. 2025GNN's Uncertainty Quantification using Self-Distillationcited by 0
  3. 2025Variational Graph Convolutional Neural Networkscited by 0
  4. 2025Supervised Learning of Random Neural Architectures Structured by Latent Random Fields on Compact Boundaryless Multiply-Connected Manifoldscited by 0
  5. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
  6. 2026NetworkNet: A Deep Neural Network Approach for Random Networks with Sparse Nodal Attributes and Complex Nodal Heterogeneitycited by 0
  7. 2026Quantile-Free Uncertainty Quantification in Graph Neural Networkscited by 0
  8. 2026Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?cited by 0