mlsanityData to 7 Oct 2026

Adaptive conformal classification with noisy labels

arXiv 2309.05092 ↗First posted 10 Sep 2023stat.ME cs.LG math.STcited by 24

Not on the map. Why?

Abstract (arXiv)

This paper develops novel conformal prediction methods for classification tasks that can automatically adapt to random label contamination in the calibration sample, leading to more informative prediction sets with stronger coverage guarantees compared to state-of-the-art approaches. This is made possible by a precise characterization of the effective coverage inflation (or deflation) suffered by standard conformal inferences in the presence of label contamination, which is then made actionable through new calibration algorithms. Our solution is flexible and can leverage different modeling assumptions about the label contamination process, while requiring no knowledge of the underlying data distribution or of the inner workings of the machine-learning classifier. The advantages of the proposed methods are demonstrated through extensive simulations and an application to object classification with the CIFAR-10H image data set.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 10 Sep 2023.

Builds on

35 of 61 references.

References · 35

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Distribution-Free Predictive Inference For Regressioncited by 657
  3. 2019Conformalized Quantile Regressioncited by 620
  4. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  5. 2019Conformal Prediction Under Covariate Shiftcited by 511
  6. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  7. 2020Classification with Valid and Adaptive Coveragecited by 390
  8. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 388
  9. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 360
  10. 2022Conformal prediction beyond exchangeabilitycited by 348
  11. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 270
  12. 2019Human uncertainty makes classification more robustcited by 231
23 more
  1. 2019Predictive inference with the jackknife+cited by 206
  2. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  3. 2020A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarioscited by 170
  4. 2020Conformal Inference of Counterfactuals and Individual Treatment Effectscited by 150
  5. 2021Testing for Outliers with Conformal p-valuescited by 133
  6. 2022Conformal Inference for Online Prediction with Arbitrary Distribution Shiftscited by 123
  7. 2019Image Classification with Deep Learning in the Presence of Noisy Labels: A Surveycited by 101
  8. 2021Conformal Prediction using Conditional Histogramscited by 77
  9. 2019A comparison of some conformal quantile regression methodscited by 76
  10. 2013Classification with Asymmetric Label Noise: Consistency and Maximal Denoisingcited by 67
  11. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 62
  12. 2021Conformalized Survival Analysiscited by 53
  13. 2019Prediction and outlier detection in classification problemscited by 44
  14. 2019With Malice Towards None: Assessing Uncertainty via Equalized Coveragecited by 43
  15. 2021Conformal Sensitivity Analysis for Individual Treatment Effectscited by 40
  16. 2018Cautious Deep Learningcited by 35
  17. 2022Integrative conformal p-values for powerful out-of-distribution testing with labeled outlierscited by 19
  18. 2023Derandomized Novelty Detection with FDR Control via Conformal E-valuescited by 15
  19. 2022Predictive Inference with Weak Supervisioncited by 13
  20. 2023Conformalized matrix completioncited by 13
  21. 2022Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queriescited by 10
  22. 2021Binary classification with corrupted labelscited by 4
  23. 2022Conformal Frequency Estimation with Sketched Datacited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 8; 2026: 10.

24 papers.

Sort:

By area:

  1. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 52
  2. 2024Conformal Prediction: A Data Perspectivecited by 25
  3. 2025Wasserstein-regularized Conformal Prediction under General Distribution Shiftcited by 14
  4. 2024Split Conformal Prediction under Data Contaminationcited by 12
  5. 2024Uncertainty quantification for probabilistic machine learning in earth observation using conformal predictioncited by 9
  6. 2025Synthetic-Powered Predictive Inferencecited by 9
  7. 2024Robust Conformal Prediction Using Privileged Informationcited by 7
  8. 2025Conformal Prediction of Classifiers with Many Classes based on Noisy Labelscited by 4
  9. 2025Exploring the Noise Robustness of Online Conformal Predictioncited by 4
  10. 2026Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judgescited by 4
  11. 2025Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weightingcited by 3
  12. 2024Meta-Analysis with Untrusted Datacited by 2
12 more
  1. 2025Privacy-Preserving Conformal Prediction Under Local Differential Privacycited by 2
  2. 2025Efficient Conformal Prediction for Regression Models under Label Noisecited by 1
  3. 2025Weighted Conformal Prediction Provides Adaptive and Valid Mask-Conditional Coverage for General Missing Data Mechanismscited by 0
  4. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
  5. 2026Label Noise Cleaning for Supervised Classification via Bernoulli Random Samplingcited by 0
  6. 2026Elements of Conformal Predictioncited by 0
  7. 2026Robust Conditional Conformal Prediction via Branched Normalizing Flowcited by 0
  8. 2026Set-Valued Policy Learningcited by 0
  9. 2026Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guaranteescited by 0
  10. 2026The Exceedance Design Effect: Effective Sample Size for Thresholds under Clusteringcited by 0
  11. 2026CHOIR: heterogeneity-aware conformal prediction for crash injury severity across driver safety stratacited by 0
  12. 2026Certified Against Which Oracle? Execution Labels Set the Reported Risk of Conformal Abstention for Text-to-SQLcited by 0