# Interpretable Regional Descriptors: Hyperbox-Based Local Explanations

arXiv: https://arxiv.org/abs/2305.02780 · HTML: https://mlsanity.com/paper/2305.02780/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Boolean Decision Rules via Column Generation](https://mlsanity.com/paper/1805.09901/) (2018)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [ANCHOR: logically-centralized security for Software-Defined Networks](https://mlsanity.com/paper/1711.03636/) (2017)
- [MAIRE -- A Model-Agnostic Interpretable Rule Extraction Procedure for Explaining Classifiers](https://mlsanity.com/paper/2011.01506/) (2020)
- [RbX: Region-based explanations of prediction models](https://mlsanity.com/paper/2210.08721/) (2022)

## Built on by (most cited first, 6 of 6)

- [Even-if Explanations: Formal Foundations, Priorities and Complexity](https://mlsanity.com/paper/2401.10938/) (2024)
- [Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computation](https://mlsanity.com/paper/2405.04081/) (2024)
- [Data Science Principles for Interpretable and Explainable AI](https://mlsanity.com/paper/2405.10552/) (2024)
- [Guarantee Regions for Local Explanations](https://mlsanity.com/paper/2402.12737/) (2024)
- [Hyperbox Mixture Regression for Process Performance Prediction in Antibody Production](https://mlsanity.com/paper/2411.01404/) (2024)
- [Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer](https://mlsanity.com/paper/2603.17534/) (2026)

## Abstract (arXiv)

This work introduces interpretable regional descriptors, or IRDs, for local, model-agnostic interpretations. IRDs are hyperboxes that describe how an observation's feature values can be changed without affecting its prediction. They justify a prediction by providing a set of "even if" arguments (semi-factual explanations), and they indicate which features affect a prediction and whether pointwise biases or implausibilities exist. A concrete use case shows that this is valuable for both machine learning modelers and persons subject to a decision. We formalize the search for IRDs as an optimization problem and introduce a unifying framework for computing IRDs that covers desiderata, initialization techniques, and a post-processing method. We show how existing hyperbox methods can be adapted to fit into this unified framework. A benchmark study compares the methods based on several quality measures and identifies two strategies to improve IRDs.