mlsanityData to 14 Oct 2026

Evidential Rule Learning for Interpretable Classification with Abstention

arXiv 2608.05859 ↗First posted 6 Aug 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence behind their decisions and abstain when they cannot decide reliably. We introduce Fast Evidential Rule Learning (FERL), a method that learns interpretable, accurate fuzzy rule models whose outputs are evidential. Unlike post-hoc calibration, FERL's belief, plausibility, and abstention capabilities arise directly from the fuzzy memberships in a single deterministic pass, with no auxiliary head, held-out set, or repeated inference. Our theoretical analysis further shows that FERL is Lipschitz stable, which means that its evidential outputs vary smoothly with the input. Against state-of-the-art rule learners, FERL is statistically significantly more accurate across a 30 tabular-dataset benchmark (+2.6% average accuracy over the second best). Its native set predictions attain the best utility-discounted accuracy among credal classifiers (u65/u80=0.80/0.83 vs. 0.79/0.80 for the naive credal classifier), at higher set coverage (0.92 vs. ≤0.82). FERL also matches dedicated out-of-distribution detectors on tabular near-OOD detection (77.7 vs. 77.4 AUROC for the strongest baseline). Under detector-class-disjoint concept-bottleneck evaluation, its it is within 2.3 AUROC points of the strongest dedicated detector on both CUB and AwA2, while attaining the best AwA2 AUPR-Out (68.3) and novel-class rejection (57.2), while being able to name which attributes are anomalous.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 63 references that are in the map. First posted on arXiv 6 Aug 2026.

Builds on

34 of 63 references.

References · 34

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2017On Calibration of Modern Neural Networkscited by 4,960
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  11. 2018Sanity Checks for Saliency Mapscited by 1,156
  12. 2020Concept Bottleneck Modelscited by 1,032
22 more
  1. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  2. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  3. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  4. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  5. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  6. 2020Classification with Valid and Adaptive Coveragecited by 396
  7. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 364
  8. 2019Deep Evidential Regressioncited by 355
  9. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  10. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  11. 2021Scalable Rule-Based Representation Learning for Interpretable Classificationcited by 40
  12. 2023Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithmscited by 36
  13. 2021Learning Accurate and Interpretable Decision Rule Sets from Neural Networkscited by 25
  14. 2021Credal Self-Supervised Learningcited by 15
  15. 2023Learning Interpretable Rules for Scalable Data Representation and Classificationcited by 14
  16. 2022Fast Interpretable Greedy-Tree Sumscited by 13
  17. 2024Credal Wrapper of Model Averaging for Uncertainty Estimation in Classificationcited by 13
  18. 2018Logistic Regression, Neural Networks and Dempster-Shafer Theory: a New Perspectivecited by 11
  19. 2018Probability Calibration Treescited by 6
  20. 2024CAM-Based Methods Can See through Wallscited by 4
  21. 2024Scalable Rule Lists Learning with Samplingcited by 4
  22. 2025Compact Rule-Based Classifier Learning via Gradient Descentcited by 2

Built on by

Not cited yet.