mlsanityData to 7 Oct 2026

ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model

arXiv 2210.08151 ↗First posted 15 Oct 2022cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the predictive performance of the model, or produce explanations that are not transparent, trustworthy or do not capture the diversity of the data. To address these shortcomings, we propose ProtoVAE, a variational autoencoder-based framework that learns class-specific prototypes in an end-to-end manner and enforces trustworthiness and diversity by regularizing the representation space and introducing an orthonormality constraint. Finally, the model is designed to be transparent by directly incorporating the prototypes into the decision process. Extensive comparisons with previous self-explainable approaches demonstrate the superiority of ProtoVAE, highlighting its ability to generate trustworthy and diverse explanations, while not degrading predictive performance.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 31 of its 60 references that are in the map. First posted on arXiv 15 Oct 2022.

Builds on

31 of 60 references.

References · 31

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  10. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  11. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  12. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
19 more
  1. 2021Understanding Dimensional Collapse in Contrastive Self-supervised Learningcited by 374
  2. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  3. 2017A Neural Representation of Sketch Drawingscited by 311
  4. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
  5. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  6. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
  7. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  8. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 120
  9. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  10. 2021Explanations in Autonomous Driving: A Surveycited by 80
  11. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 72
  12. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
  13. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  14. 2019A Rate-Distortion Framework for Explaining Neural Network Decisionscited by 24
  15. 2020A Framework to Learn with Interpretationcited by 23
  16. 2021Self-Interpretable Model with TransformationEquivariant Interpretationcited by 21
  17. 2020Towards a Theoretical Understanding of the Robustness of Variational Autoencoderscited by 17
  18. 2019Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Modelscited by 5
  19. 2022Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 13; 2025: 9; 2026: 4.

34 papers.

Sort:

By area:

  1. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  2. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  3. 2023Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Sciencecited by 25
  4. 2024Explaining Time Series via Contrastive and Locally Sparse Perturbationscited by 22
  5. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  6. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  7. 2023Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognitioncited by 11
  8. 2026SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinementcited by 11
  9. 2024ProtoS-ViT: Visual foundation models for sparse self-explainable classificationscited by 8
  10. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  11. 2024The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanationscited by 5
  12. 2025DocVXQA: Context-Aware Visual Explanations for Document Question Answeringcited by 5
22 more
  1. 2024Pantypes: Diverse Representatives for Self-Explainable Modelscited by 4
  2. 2024Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentationcited by 4
  3. 2024Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddingscited by 4
  4. 2024Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretationcited by 4
  5. 2023Interpretable Alzheimer's Disease Classification Via a Contrastive Diffusion Autoencodercited by 3
  6. 2024This Probably Looks Exactly Like That: An Invertible Prototypical Networkcited by 3
  7. 2024DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimationcited by 2
  8. 2024Restyling Unsupervised Concept Based Interpretable Networks with Generative Modelscited by 2
  9. 2024Advancing Interpretability in Text Classification through Prototype Learningcited by 2
  10. 2025Self-Explaining Hypergraph Neural Networks for Diagnosis Predictioncited by 2
  11. 2025Tell me why: Visual foundation models as self-explainable classifierscited by 2
  12. 2023Human-Guided Complexity-Controlled Abstractionscited by 1
  13. 2024A Note on Bias to Completecited by 1
  14. 2025Comprehensive Evaluation of Prototype Neural Networkscited by 1
  15. 2025CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimationcited by 1
  16. 2026This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapsecited by 1
  17. 2024Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networkscited by 0
  18. 2025Fixed Point Explainabilitycited by 0
  19. 2025Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detectioncited by 0
  20. 2025Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Trainingcited by 0
  21. 2026Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hullscited by 0
  22. 2026ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterizationcited by 0