mlsanityData to 7 Oct 2026

Interpretations are useful: penalizing explanations to align neural networks with prior knowledge

arXiv 1909.13584 ↗First posted 30 Sep 2019cs.LG cs.CV stat.MLcited by 144

Not on the map. Why?

Abstract (arXiv)

For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning methods stop at the first step, providing practitioners with insight into a model, but no way to act on it. In this paper, we propose contextual decomposition explanation penalization (CDEP), a method which enables practitioners to leverage existing explanation methods in order to increase the predictive accuracy of deep learning models. In particular, when shown that a model has incorrectly assigned importance to some features, CDEP enables practitioners to correct these errors by directly regularizing the provided explanations. Using explanations provided by contextual decomposition (CD) (Murdoch et al., 2018), we demonstrate the ability of our method to increase performance on an array of toy and real datasets.

Key facts. Cited by 144 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 31; 2023: 38; 2024: 22; 2025: 15; 2026: 12.

144 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  2. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  3. 2022Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goalscited by 120
  4. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  5. 2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMscited by 82
  6. 2021Fairness via Representation Neutralizationcited by 63
  7. 2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59
  8. 2022Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlationcited by 59
  9. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  10. 2022Concept-level Debugging of Part-Prototype Networkscited by 52
  11. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  12. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
38 more
  1. 2021Shapley Explanation Networkscited by 41
  2. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  3. 2021Finding and Fixing Spurious Patterns with Explanationscited by 38
  4. 2021Fast Axiomatic Attribution for Neural Networkscited by 35
  5. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
  6. 2022Using Language to Extend to Unseen Domainscited by 34
  7. 2021Adaptive wavelet distillation from neural networks through interpretationscited by 32
  8. 2021Towards Robust Classification Model by Counterfactual and Invariant Data Generationcited by 30
  9. 2022On Guiding Visual Attention with Language Specificationcited by 30
  10. 2023Learning to Intervene on Concept Bottleneckscited by 29
  11. 2021Refining Language Models with Compositional Explanationscited by 27
  12. 2023Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decisioncited by 27
  13. 2021What to Learn, and How: Toward Effective Learning from Rationalescited by 25
  14. 2021Self-Interpretable Model with TransformationEquivariant Interpretationcited by 21
  15. 2022A survey, review, and future trends of skin lesion segmentation and classificationcited by 20
  16. 2023From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Spacecited by 20
  17. 2021Consistent Explanations by Contrastive Learningcited by 18
  18. 2023Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Modelscited by 17
  19. 2023Learning by Self-Explainingcited by 17
  20. 2023Studying How to Efficiently and Effectively Guide Models with Explanationscited by 16
  21. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  22. 2022A survey on improving NLP models with human explanationscited by 15
  23. 2021Explainable Machine Learning with Prior Knowledge: An Overviewcited by 14
  24. 2022On the Relationship Between Explanation and Prediction: A Causal Viewcited by 14
  25. 2023Explainable GeoAI: Can saliency maps help interpret artificial intelligence's learning process? An empirical study on natural feature detectioncited by 14
  26. 2023Are Data-driven Explanations Robust against Out-of-distribution Data?cited by 14
  27. 2023Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillationcited by 14
  28. 2024DEAL: Disentangle and Localize Concept-level Explanations for VLMscited by 14
  29. 2024Contestable AI needs Computational Argumentationcited by 12
  30. 2023Interpreting and Correcting Medical Image Classification with PIP-Netcited by 11
  31. 2021Towards Benchmarking the Utility of Explanations for Model Debuggingcited by 10
  32. 2021Matching Learned Causal Effects of Neural Networks with Domain Priorscited by 10
  33. 2022Knowledge-augmented Deep Learning and Its Applications: A Surveycited by 10
  34. 2021Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualitiescited by 9
  35. 2023Preemptively Pruning Clever-Hans Strategies in Deep Neural Networkscited by 9
  36. 2023Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?cited by 9
  37. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 9
  38. 2024Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotationscited by 9

50 most cited of 144 All 144 (JSON)