# Use Perturbations when Learning from Explanations

arXiv: https://arxiv.org/abs/2303.06419 · HTML: https://mlsanity.com/paper/2303.06419/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 11 Mar 2023.

## Builds on (most cited first, 30 of 33)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models](https://mlsanity.com/paper/1810.12715/) (2018)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Towards Stable and Efficient Training of Verifiably Robust Neural Networks](https://mlsanity.com/paper/1906.06316/) (2019)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded](https://mlsanity.com/paper/1902.03751/) (2019)
- [Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals](https://mlsanity.com/paper/2210.01790/) (2022)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations](https://mlsanity.com/paper/2011.12854/) (2020)
- [Hierarchical interpretations for neural network predictions](https://mlsanity.com/paper/1806.05337/) (2018)
- [Bayesian Inference with Certifiable Adversarial Robustness](https://mlsanity.com/paper/2102.05289/) (2021)
- [Focus on the Common Good: Group Distributional Robustness Follows](https://mlsanity.com/paper/2110.02619/) (2021)
- [Robust Explanation Constraints for Neural Networks](https://mlsanity.com/paper/2212.08507/) (2022)

## Built on by (most cited first, 2 of 2)

- [Targeted Activation Penalties Help CNNs Ignore Spurious Signals](https://mlsanity.com/paper/2311.12813/) (2023)
- [Model Guidance via Robust Feature Attribution](https://mlsanity.com/paper/2506.19680/) (2025)

## Abstract (arXiv)

Machine learning from explanations (MLX) is an approach to learning that uses human-provided explanations of relevant or irrelevant features for each input to ensure that model predictions are right for the right reasons. Existing MLX approaches rely on local model interpretation methods and require strong model smoothing to align model and human explanations, leading to sub-optimal performance. We recast MLX as a robustness problem, where human explanations specify a lower dimensional manifold from which perturbations can be drawn, and show both theoretically and empirically how this approach alleviates the need for strong model smoothing. We consider various approaches to achieving robustness, leading to improved performance over prior MLX methods. Finally, we show how to combine robustness with an earlier MLX method, yielding state-of-the-art results on both synthetic and real-world benchmarks.