# Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models

arXiv: https://arxiv.org/abs/2111.04658 · HTML: https://mlsanity.com/paper/2111.04658/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 8 Nov 2021.

## Builds on (most cited first, 20 of 20)

- [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)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [A Symbolic Approach to Explaining Bayesian Network Classifiers](https://mlsanity.com/paper/1805.03364/) (2018)
- [On The Reasons Behind Decisions](https://mlsanity.com/paper/2002.09284/) (2020)
- [Consistency of random forests](https://mlsanity.com/paper/1405.2881/) (2014)
- [Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations](https://mlsanity.com/paper/2103.01890/) (2021)
- [On Validating, Repairing and Refining Heuristic ML Explanations](https://mlsanity.com/paper/1907.02509/) (2019)
- [On Locality of Local Explanation Models](https://mlsanity.com/paper/2106.14648/) (2021)
- [Interpretable Random Forests via Rule Extraction](https://mlsanity.com/paper/2004.14841/) (2020)
- [SHAFF: Fast and consistent SHApley eFfect estimates via random Forests](https://mlsanity.com/paper/2105.11724/) (2021)
- [Do Not Trust Additive Explanations](https://mlsanity.com/paper/1903.11420/) (2019)
- [Sparse learning with CART](https://mlsanity.com/paper/2006.04266/) (2020)
- [MDA for random forests: inconsistency, and a practical solution via the Sobol-MDA](https://mlsanity.com/paper/2102.13347/) (2021)
- [Accurate Shapley Values for explaining tree-based models](https://mlsanity.com/paper/2106.03820/) (2021)
- [Wasserstein Random Forests and Applications in Heterogeneous Treatment Effects](https://mlsanity.com/paper/2006.04709/) (2020)

## Built on by (most cited first, 4 of 4)

- [A Sea of Words: An In-Depth Analysis of Anchors for Text Data](https://mlsanity.com/paper/2205.13789/) (2022)
- [Faithful and Robust Local Interpretability for Textual Predictions](https://mlsanity.com/paper/2311.01605/) (2023)
- [Understanding Post-hoc Explainers: The Case of Anchors](https://mlsanity.com/paper/2303.08806/) (2023)
- [Local and Regional Counterfactual Rules: Summarized and Robust Recourses](https://mlsanity.com/paper/2209.14568/) (2022)

## Abstract (arXiv)

To explain the decision of any model, we extend the notion of probabilistic Sufficient Explanations (P-SE). For each instance, this approach selects the minimal subset of features that is sufficient to yield the same prediction with high probability, while removing other features. The crux of P-SE is to compute the conditional probability of maintaining the same prediction. Therefore, we introduce an accurate and fast estimator of this probability via random Forests for any data (boldsymbolX, Y) and show its efficiency through a theoretical analysis of its consistency. As a consequence, we extend the P-SE to regression problems. In addition, we deal with non-discrete features, without learning the distribution of boldsymbolX nor having the model for making predictions. Finally, we introduce local rule-based explanations for regression/classification based on the P-SE and compare our approaches w.r.t other explainable AI methods. These methods are available as a Python package at urlwww.github.com/salimamoukou/acv00.