# Streamlining models with explanations in the learning loop

arXiv: https://arxiv.org/abs/2302.07760 · HTML: https://mlsanity.com/paper/2302.07760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 15 Feb 2023.

## Builds on (most cited first, 19 of 19)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Towards Explainable Artificial Intelligence](https://mlsanity.com/paper/1909.12072/) (2019)
- [When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data](https://mlsanity.com/paper/2102.02201/) (2021)
- [A Framework for Learning Ante-hoc Explainable Models via Concepts](https://mlsanity.com/paper/2108.11761/) (2021)
- [To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods](https://mlsanity.com/paper/2106.00461/) (2021)
- [FairLens: Auditing Black-box Clinical Decision Support Systems](https://mlsanity.com/paper/2011.04049/) (2020)
- [Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity](https://mlsanity.com/paper/2105.04854/) (2021)
- [Can Explanations Be Useful for Calibrating Black Box Models?](https://mlsanity.com/paper/2110.07586/) (2021)
- [Reflective-Net: Learning from Explanations](https://mlsanity.com/paper/2011.13986/) (2020)
- [An empirical study of the effect of background data size on the stability of SHapley Additive exPlanations (SHAP) for deep learning models](https://mlsanity.com/paper/2204.11351/) (2022)

## Abstract (arXiv)

Several explainable AI methods allow a Machine Learning user to get insights on the classification process of a black-box model in the form of local linear explanations. With such information, the user can judge which features are locally relevant for the classification outcome, and get an understanding of how the model reasons. Standard supervised learning processes are purely driven by the original features and target labels, without any feedback loop informed by the local relevance of the features identified by the post-hoc explanations. In this paper, we exploit this newly obtained information to design a feature engineering phase, where we combine explanations with feature values. To do so, we develop two different strategies, named Iterative Dataset Weighting and Targeted Replacement Values, which generate streamlined models that better mimic the explanation process presented to the user. We show how these streamlined models compare to the original black-box classifiers, in terms of accuracy and compactness of the newly produced explanations.