mlsanityData to 14 Oct 2026

Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time

arXiv 2503.01087 ↗First posted 3 Mar 2025cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Interpretability is critical for machine learning models in high-stakes settings because it allows users to verify the model's reasoning. In computer vision, prototypical part models (ProtoPNets) have become the dominant model type to meet this need. Users can easily identify flaws in ProtoPNets, but fixing problems in a ProtoPNet requires slow, difficult retraining that is not guaranteed to resolve the issue. This problem is called the "interaction bottleneck." We solve the interaction bottleneck for ProtoPNets by simultaneously finding many equally good ProtoPNets (i.e., a draw from a "Rashomon set"). We show that our framework - called Proto-RSet - quickly produces many accurate, diverse ProtoPNets, allowing users to correct problems in real time while maintaining performance guarantees with respect to the training set. We demonstrate the utility of this method in two settings: 1) removing synthetic bias introduced to a bird identification model and 2) debugging a skin cancer identification model. This tool empowers non-machine-learning experts, such as clinicians or domain experts, to quickly refine and correct machine learning models without repeated retraining by machine learning experts.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 41 of its 59 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

41 of 59 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  5. 2020Concept Bottleneck Modelscited by 1,032
  6. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  7. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
  8. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  9. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  10. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 214
  11. 2019Predictive Multiplicity in Classificationcited by 166
  12. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
29 more
  1. 2019On the Existence of Simpler Machine Learning Modelscited by 89
  2. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  3. 2022B-cos Networks: Alignment is All We Need for Interpretabilitycited by 88
  4. 2022Exploring the Whole Rashomon Set of Sparse Decision Treescited by 81
  5. 2021IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammographycited by 72
  6. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  7. 2024Amazing Things Come From Having Many Good Modelscited by 55
  8. 2022Concept-level Debugging of Part-Prototype Networkscited by 52
  9. 2020This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognitioncited by 50
  10. 2022Rashomon Capacity: A Metric for Predictive Multiplicity in Classificationcited by 47
  11. 2022Predictive Multiplicity in Probabilistic Classificationcited by 44
  12. 2022Visual correspondence-based explanations improve AI robustness and human-AI team accuracycited by 39
  13. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  14. 2022Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networkscited by 37
  15. 2023This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizationscited by 36
  16. 2023A Path to Simpler Models Starts With Noisecited by 33
  17. 2023Exploring and Interacting with the Set of Good Sparse Generalized Additive Modelscited by 30
  18. 2023The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importancecited by 29
  19. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
  20. 2022FasterRisk: Fast and Accurate Interpretable Risk Scorescited by 21
  21. 2023Arbitrary Decisions are a Hidden Cost of Differentially Private Trainingcited by 19
  22. 2023MProtoNet: A Case-Based Interpretable Model for Brain Tumor Classification with 3D Multi-parametric Magnetic Resonance Imagingcited by 11
  23. 2023Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraintscited by 11
  24. 2023Exploration of the Rashomon Set Assists Trustworthy Explanations for Medical Datacited by 11
  25. 2024This Looks Better than That: Better Interpretable Models with ProtoPNeXtcited by 11
  26. 2022Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learningcited by 10
  27. 2024Efficient Exploration of the Rashomon Set of Rule Set Modelscited by 10
  28. 2023Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retrainingcited by 3
  29. 2024FPN-IAIA-BL: A Multi-Scale Interpretable Deep Learning Model for Classification of Mass Margins in Digital Mammographycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

  1. 2025Credal Prediction based on Relative Likelihoodcited by 8
  2. 2026Unsupervised Causal Prototypical Networks for De-biased Interpretable Dermoscopy Diagnosiscited by 4
  3. 2025Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effectcited by 3
  4. 2025Debugging Concept Bottleneck Models through Removal and Retrainingcited by 2
  5. 2026ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Setscited by 2
  6. 2025Parameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck Modelscited by 1
  7. 2026REALITrees: Rashomon Ensemble Active Learning for Interpretable Treescited by 1
  8. 2025Efficient & Correct Predictive Equivalence for Decision Treescited by 0
  9. 2025What You See is (Usually) What You Get: Multimodal Prototype Networks that Abstain from Expensive Modalitiescited by 0
  10. 2025The Double-Edged Nature of the Rashomon Set for Trustworthy Machine Learningcited by 0
  11. 2026ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classificationcited by 0
  12. 2026From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal k-Sparse GLMscited by 0
1 more
  1. 2026ArborEnum: Decision Tree Rashomon Sets over Continuous Featurescited by 0