mlsanityData to 7 Oct 2026

Editing a classifier by rewriting its prediction rules

arXiv 2112.01008 ↗First posted 2 Dec 2021cs.LG cs.CVcited by 64

Not on the map. Why?

Abstract (arXiv)

We present a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our approach requires virtually no additional data collection and can be applied to a variety of settings, including adapting a model to new environments, and modifying it to ignore spurious features. Our code is available at https://github.com/MadryLab/EditingClassifiers .

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 63 of its 97 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

63 of 97 references.

References · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  11. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  12. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
38 more
  1. 2019Invariant Risk Minimizationcited by 1,832
  2. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  4. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  5. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  6. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  7. 2020Concept Bottleneck Modelscited by 1,022
  8. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  9. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  10. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  11. 2018Recognition in Terra Incognitacited by 655
  12. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  13. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  14. 2021Editing Factual Knowledge in Language Modelscited by 548
  15. 2021Fast Model Editing at Scalecited by 491
  16. 2015Optimal Transport for Domain Adaptationcited by 457
  17. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 428
  18. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  19. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 342
  20. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
  21. 2020Are we done with ImageNet?cited by 329
  22. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  23. 2019Counterfactual Visual Explanationscited by 312
  24. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  25. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  26. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 254
  27. 2019On the "steerability" of generative adversarial networkscited by 247
  28. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  29. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  30. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  31. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  32. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  33. 2019Distributionally Robust Language Modelingcited by 142
  34. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  35. 2019Adversarial Examples Are a Natural Consequence of Test Error in Noisecited by 114
  36. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  37. 2019Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editingcited by 108
  38. 2019Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentationcited by 105

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 18; 2023: 19; 2024: 19; 2025: 4; 2026: 4.

64 papers.

Sort:

By area:

  1. 2022Editing Models with Task Arithmeticcited by 1,076
  2. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  3. 2022Post-hoc Concept Bottleneck Modelscited by 289
  4. 2023Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Modelscited by 237
  5. 2023Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Modelscited by 218
  6. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  7. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  8. 2022Patching open-vocabulary models by interpolating weightscited by 187
  9. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  10. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Modelscited by 128
  11. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  12. 2024Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Modelscited by 122
38 more
  1. 2023Parameter Efficient Multi-task Model Fusion with Partial Linearizationcited by 64
  2. 2023Continual Learning: Applications and the Road Forwardcited by 59
  3. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  4. 2022Mechanistic Mode Connectivitycited by 50
  5. 2023Codebook Features: Sparse and Discrete Interpretability for Neural Networkscited by 45
  6. 2022Using Language to Extend to Unseen Domainscited by 34
  7. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 33
  8. 2023ReFACT: Updating Text-to-Image Models by Editing the Text Encodercited by 32
  9. 2022Repairing Neural Networks by Leaving the Right Past Behindcited by 27
  10. 2022Language Anisotropic Cross-Lingual Model Editingcited by 26
  11. 2022Rewriting Geometric Rules of a GANcited by 25
  12. 2023Overcoming Generic Knowledge Loss with Selective Parameter Updatecited by 23
  13. 2024Decomposing and Editing Predictions by Modeling Model Computationcited by 19
  14. 2024Concept Bottleneck Models Without Predefined Conceptscited by 17
  15. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  16. 2023Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Modelscited by 15
  17. 2024Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmeticcited by 14
  18. 2023Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?cited by 13
  19. 2022Artifact-Based Domain Generalization of Skin Lesion Modelscited by 11
  20. 2023Interpreting and Controlling Vision Foundation Models via Text Explanationscited by 11
  21. 2023A Framework for Interpretability in Machine Learning for Medical Imagingcited by 9
  22. 2024Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampeningcited by 9
  23. 2023Edit at your own risk: evaluating the robustness of edited models to distribution shiftscited by 8
  24. 2024Clarify: Improving Model Robustness With Natural Language Correctionscited by 8
  25. 2022Perspectives on Incorporating Expert Feedback into Model Updatescited by 7
  26. 2022Rank-One Editing of Encoder-Decoder Modelscited by 7
  27. 2024Towards Compositionality in Concept Learningcited by 7
  28. 2024Towards Practical Tool Usage for Continually Learning LLMscited by 6
  29. 2022Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behaviorcited by 5
  30. 2024Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppressioncited by 5
  31. 2024Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selectioncited by 5
  32. 2024Learning Where to Edit Vision Transformerscited by 4
  33. 2025How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyondcited by 4
  34. 2022Data-Centric Debugging: mitigating model failures via targeted data collectioncited by 3
  35. 2023Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generationcited by 3
  36. 2026Attribution-Guided Model Rectification of Unreliable Neural Network Behaviorscited by 3
  37. 2023Transferring Learning Trajectories of Neural Networkscited by 2
  38. 2024DREditor: An Time-efficient Approach for Building a Domain-specific Dense Retrieval Modelcited by 2

50 most cited of 64 All 64 (JSON)