# REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values

arXiv: https://arxiv.org/abs/2403.08880 · HTML: https://mlsanity.com/paper/2403.08880/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 55 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 23 of 23)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models](https://mlsanity.com/paper/2011.01625/) (2020)
- [On the Privacy Risks of Algorithmic Fairness](https://mlsanity.com/paper/2011.03731/) (2020)
- [Shapley values for feature selection: The good, the bad, and the axioms](https://mlsanity.com/paper/2102.10936/) (2021)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [A Comprehensive Evaluation Framework for Deep Model Robustness](https://mlsanity.com/paper/2101.09617/) (2021)
- [Explainability for fair machine learning](https://mlsanity.com/paper/2010.07389/) (2020)
- [Principles to Practices for Responsible AI: Closing the Gap](https://mlsanity.com/paper/2006.04707/) (2020)
- [Causal Feature Selection for Algorithmic Fairness](https://mlsanity.com/paper/2006.06053/) (2020)
- [CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection](https://mlsanity.com/paper/2102.05311/) (2021)
- [On the Legal Compatibility of Fairness Definitions](https://mlsanity.com/paper/1912.00761/) (2019)
- [FaiR-N: Fair and Robust Neural Networks for Structured Data](https://mlsanity.com/paper/2010.06113/) (2020)
- [Fairness Under Feature Exemptions: Counterfactual and Observational Measures](https://mlsanity.com/paper/2006.07986/) (2020)
- [Fast Feature Selection with Fairness Constraints](https://mlsanity.com/paper/2202.13718/) (2022)
- [FEAMOE: Fair, Explainable and Adaptive Mixture of Experts](https://mlsanity.com/paper/2210.04995/) (2022)
- [Quantifying Feature Contributions to Overall Disparity Using Information Theory](https://mlsanity.com/paper/2206.08454/) (2022)

## Built on by (most cited first, 1 of 1)

- [AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing](https://mlsanity.com/paper/2505.17380/) (2025)

## Abstract (arXiv)

Feature selection is a crucial step in building machine learning models. This process is often achieved with accuracy as an objective, and can be cumbersome and computationally expensive for large-scale datasets. Several additional model performance characteristics such as fairness and robustness are of importance for model development. As regulations are driving the need for more trustworthy models, deployed models need to be corrected for model characteristics associated with responsible artificial intelligence. When feature selection is done with respect to one model performance characteristic (eg. accuracy), feature selection with secondary model performance characteristics (eg. fairness and robustness) as objectives would require going through the computationally expensive selection process from scratch. In this paper, we introduce the problem of feature reselection, so that features can be selected with respect to secondary model performance characteristics efficiently even after a feature selection process has been done with respect to a primary objective. To address this problem, we propose REFRESH, a method to reselect features so that additional constraints that are desirable towards model performance can be achieved without having to train several new models. REFRESH's underlying algorithm is a novel technique using SHAP values and correlation analysis that can approximate for the predictions of a model without having to train these models. Empirical evaluations on three datasets, including a large-scale loan defaulting dataset show that REFRESH can help find alternate models with better model characteristics efficiently. We also discuss the need for reselection and REFRESH based on regulation desiderata.