mlsanityData to 14 Oct 2026

This Probably Looks Exactly Like That: An Invertible Prototypical Network

arXiv 2407.12200 ↗First posted 16 Jul 2024cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural network, represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations, but a human-machine semantic gap continues to haunt current approaches. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. From this, we posit that invertibly learning prototypes as distributions over the latent space provides more robust, expressive, and interpretable modeling. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models. ProtoFlow (1) sets a new state-of-the-art in joint generative and predictive modeling and (2) achieves predictive performance comparable to existing prototypical neural networks while enabling richer interpretation.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 58 of its 88 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

58 of 88 references.

References · 58

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2015Variational Inference with Normalizing Flowscited by 2,170
  7. 2016Density estimation using Real NVPcited by 2,042
  8. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  9. 2016Concrete Problems in AI Safetycited by 1,642
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  11. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  12. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
38 more
  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2020Concept Bottleneck Modelscited by 1,032
  3. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  4. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  5. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 306
  6. 2015A note on the evaluation of generative modelscited by 292
  7. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 264
  8. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  9. 2022A Survey on Generative Diffusion Modelcited by 240
  10. 2022Diffusion Probabilistic Modeling for Video Generationcited by 238
  11. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  12. 2018i-RevNet: Deep Invertible Networkscited by 137
  13. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  14. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  15. 2022CARD: Classification and Regression Diffusion Modelscited by 103
  16. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
  17. 2020A Survey on Generative Adversarial Networks: Variants, Applications, and Trainingcited by 97
  18. 2019Semi-Supervised Learning with Normalizing Flowscited by 76
  19. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  20. 2017SeGAN: Segmenting and Generating the Invisiblecited by 60
  21. 2020Towards falsifiable interpretability researchcited by 53
  22. 2021Score-Based Generative Classifierscited by 53
  23. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 50
  24. 2021Densely connected normalizing flowscited by 49
  25. 2023OmniVec: Learning robust representations with cross modal sharingcited by 44
  26. 2021ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Modelscited by 43
  27. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  28. 2022Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networkscited by 37
  29. 2023This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizationscited by 36
  30. 2022ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Modelcited by 34
  31. 2023Reversible Vision Transformerscited by 33
  32. 2023DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classificationcited by 32
  33. 2019Understanding the Limitations of Conditional Generative Modelscited by 28
  34. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  35. 2020A Framework to Learn with Interpretationcited by 23
  36. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  37. 2019Semi-Conditional Normalizing Flows for Semi-Supervised Learningcited by 15
  38. 2019Gradient-based training of Gaussian Mixture Models for High-Dimensional Streaming Datacited by 13

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3
  2. 2025Comprehensive Evaluation of Prototype Neural Networkscited by 1
  3. 2026Beyond L2: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architecturescited by 0