mlsanityData to 7 Oct 2026

Distribution Free Prediction Sets for Node Classification

arXiv 2211.14555 ↗First posted 26 Nov 2022stat.ML cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are able to achieve high classification accuracy on many important real world datasets, but provide no rigorous notion of predictive uncertainty. Quantifying the confidence of GNN models is difficult due to the dependence between datapoints induced by the graph structure. We leverage recent advances in conformal prediction to construct prediction sets for node classification in inductive learning scenarios. We do this by taking an existing approach for conformal classification that relies on textitexchangeable data and modifying it by appropriately weighting the conformal scores to reflect the network structure. We show through experiments on standard benchmark datasets using popular GNN models that our approach provides tighter and better calibrated prediction sets than a naive application of conformal prediction.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 26 Nov 2022.

Builds on

30 of 39 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  7. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  8. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  9. 2016Distribution-Free Predictive Inference For Regressioncited by 657
  10. 2019Conformalized Quantile Regressioncited by 620
  11. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  12. 2020Classification with Valid and Adaptive Coveragecited by 390
18 more
  1. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 365
  2. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 360
  3. 2022Conformal prediction beyond exchangeabilitycited by 348
  4. 2022Conformal Risk Controlcited by 290
  5. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 270
  6. 2020Graph Neural Networks with Heterophilycited by 202
  7. 2022Adaptive Conformal Predictions for Time Seriescited by 155
  8. 2020Bayesian Neural Networks: An Introduction and Surveycited by 130
  9. 2022Conformal Inference for Online Prediction with Arbitrary Distribution Shiftscited by 123
  10. 2021Learning Optimal Conformal Classifierscited by 108
  11. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  12. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 88
  13. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  14. 2022Practical Adversarial Multivalid Conformal Predictioncited by 65
  15. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 62
  16. 2018Distribution-Free Prediction Sets for Two-Layer Hierarchical Modelscited by 34
  17. 2022Predictive Inference with Feature Conformal Predictioncited by 33
  18. 2021Bayesian graph convolutional neural networks via tempered MCMCcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 13; 2025: 8; 2026: 4.

28 papers.

Sort:

By area:

  1. 2023Uncertainty Quantification over Graph with Conformalized Graph Neural Networkscited by 79
  2. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 52
  3. 2024Conformal Prediction: A Data Perspectivecited by 25
  4. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  5. 2024Split Conformal Prediction under Data Contaminationcited by 12
  6. 2024Conformal Load Prediction with Transductive Graph Autoencoderscited by 11
  7. 2025Relational Conformal Prediction for Correlated Time Seriescited by 11
  8. 2024TorchCP: A Python Library for Conformal Predictioncited by 9
  9. 2024Conformalized Link Prediction on Graph Neural Networkscited by 9
  10. 2024Conformal Inductive Graph Neural Networkscited by 9
  11. 2024Similarity-Navigated Conformal Prediction for Graph Neural Networkscited by 7
  12. 2024Valid Conformal Prediction for Dynamic GNNscited by 6
16 more
  1. 2025Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Trainingcited by 6
  2. 2025Enhanced Route Planning with Calibrated Uncertainty Setcited by 5
  3. 2023On the Temperature of Bayesian Graph Neural Networks for Conformal Predictioncited by 4
  4. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  5. 2025Topology-Aware Conformal Prediction for Stream Networkscited by 3
  6. 2025Non-exchangeable Conformal Prediction for Temporal Graph Neural Networkscited by 3
  7. 2025Residual Reweighted Conformal Prediction for Graph Neural Networkscited by 2
  8. 2024Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphscited by 1
  9. 2025Conformalized Gaussian processes for online uncertainty quantification over graphscited by 1
  10. 2024Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Informationcited by 0
  11. 2024Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networkscited by 0
  12. 2025Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictorscited by 0
  13. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
  14. 2026GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphscited by 0
  15. 2026Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detectioncited by 0
  16. 2026Conformal Individual Treatment Effect Estimation under Networked Interferencecited by 0