# Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression

arXiv: https://arxiv.org/abs/2404.09601 · HTML: https://mlsanity.com/paper/2404.09601/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 15 Apr 2024.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation](https://mlsanity.com/paper/2306.07304/) (2023)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Towards Best Practice in Explaining Neural Network Decisions with LRP](https://mlsanity.com/paper/1910.09840/) (2019)
- [Editing a classifier by rewriting its prediction rules](https://mlsanity.com/paper/2112.01008/) (2021)
- [Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy](https://mlsanity.com/paper/2106.13200/) (2021)
- [FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods](https://mlsanity.com/paper/2308.06248/) (2023)
- [Probing Classifiers are Unreliable for Concept Removal and Detection](https://mlsanity.com/paper/2207.04153/) (2022)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [Embedding Human Knowledge into Deep Neural Network via Attention Map](https://mlsanity.com/paper/1905.03540/) (2019)
- [Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence](https://mlsanity.com/paper/2202.03482/) (2022)
- [Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations](https://mlsanity.com/paper/2311.16681/) (2023)
- [From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space](https://mlsanity.com/paper/2308.09437/) (2023)

## Built on by (most cited first, 5 of 5)

- [Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples](https://mlsanity.com/paper/2510.17524/) (2025)
- [Preserving Task-Relevant Information Under Linear Concept Removal](https://mlsanity.com/paper/2506.10703/) (2025)
- [On The Variability of Concept Activation Vectors](https://mlsanity.com/paper/2509.24058/) (2025)
- [Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data](https://mlsanity.com/paper/2501.13818/) (2025)
- [Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations](https://mlsanity.com/paper/2503.05522/) (2025)

## Abstract (arXiv)

Deep Neural Networks are prone to learning and relying on spurious correlations in the training data, which, for high-risk applications, can have fatal consequences. Various approaches to suppress model reliance on harmful features have been proposed that can be applied post-hoc without additional training. Whereas those methods can be applied with efficiency, they also tend to harm model performance by globally shifting the distribution of latent features. To mitigate unintended overcorrection of model behavior, we propose a reactive approach conditioned on model-derived knowledge and eXplainable Artificial Intelligence (XAI) insights. While the reactive approach can be applied to many post-hoc methods, we demonstrate the incorporation of reactivity in particular for P-ClArC (Projective Class Artifact Compensation), introducing a new method called R-ClArC (Reactive Class Artifact Compensation). Through rigorous experiments in controlled settings (FunnyBirds) and with a real-world dataset (ISIC2019), we show that introducing reactivity can minimize the detrimental effect of the applied correction while simultaneously ensuring low reliance on spurious features.