# Interpretable & Explorable Approximations of Black Box Models

arXiv: https://arxiv.org/abs/1707.01154 · HTML: https://mlsanity.com/paper/1707.01154/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2017.

## Built on by (most cited first, 30 of 54)

- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Human-Centered Explainable AI (XAI): From Algorithms to User Experiences](https://mlsanity.com/paper/2110.10790/) (2021)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations](https://mlsanity.com/paper/2103.01890/) (2021)
- [Determinants of LLM-assisted Decision-Making](https://mlsanity.com/paper/2402.17385/) (2024)
- [GLocalX -- From Local to Global Explanations of Black Box AI Models](https://mlsanity.com/paper/2101.07685/) (2021)
- [The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations](https://mlsanity.com/paper/2205.03295/) (2022)
- [HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks](https://mlsanity.com/paper/2102.02515/) (2021)
- [Counterfactual Explanations for Models of Code](https://mlsanity.com/paper/2111.05711/) (2021)
- [Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey](https://mlsanity.com/paper/2108.09003/) (2021)
- [A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?](https://mlsanity.com/paper/2304.04780/) (2023)
- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Levels of explainable artificial intelligence for human-aligned conversational explanations](https://mlsanity.com/paper/2107.03178/) (2021)
- [An Objective Metric for Explainable AI: How and Why to Estimate the Degree of Explainability](https://mlsanity.com/paper/2109.05327/) (2021)
- [Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View](https://mlsanity.com/paper/2112.02625/) (2021)
- [Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence](https://mlsanity.com/paper/2112.14466/) (2021)
- [Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities](https://mlsanity.com/paper/2210.11846/) (2022)
- [Label-Descriptive Patterns and Their Application to Characterizing Classification Errors](https://mlsanity.com/paper/2110.09599/) (2021)
- [A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Act](https://mlsanity.com/paper/2110.11168/) (2021)
- [Probabilistic Dataset Reconstruction from Interpretable Models](https://mlsanity.com/paper/2308.15099/) (2023)
- [Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond](https://mlsanity.com/paper/2309.00064/) (2023)
- [A Review of Explainable Artificial Intelligence in Manufacturing](https://mlsanity.com/paper/2107.02295/) (2021)
- [Visual Exploration of Machine Learning Model Behavior with Hierarchical Surrogate Rule Sets](https://mlsanity.com/paper/2201.07724/) (2022)
- [Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models](https://mlsanity.com/paper/2203.16073/) (2022)
- [Efficient Learning of Interpretable Classification Rules](https://mlsanity.com/paper/2205.06936/) (2022)
- [Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods](https://mlsanity.com/paper/2303.04437/) (2023)
- [Interpretable Graph Neural Networks for Tabular Data](https://mlsanity.com/paper/2308.08945/) (2023)
- [When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis](https://mlsanity.com/paper/2106.00954/) (2021)
- [Deep Learning, Natural Language Processing, and Explainable Artificial Intelligence in the Biomedical Domain](https://mlsanity.com/paper/2202.12678/) (2022)
- [Interpreting Black-box Machine Learning Models for High Dimensional Datasets](https://mlsanity.com/paper/2208.13405/) (2022)

## Abstract (arXiv)

We propose Black Box Explanations through Transparent Approximations (BETA), a novel model agnostic framework for explaining the behavior of any black-box classifier by simultaneously optimizing for fidelity to the original model and interpretability of the explanation. To this end, we develop a novel objective function which allows us to learn (with optimality guarantees), a small number of compact decision sets each of which explains the behavior of the black box model in unambiguous, well-defined regions of feature space. Furthermore, our framework also is capable of accepting user input when generating these approximations, thus allowing users to interactively explore how the black-box model behaves in different subspaces that are of interest to the user. To the best of our knowledge, this is the first approach which can produce global explanations of the behavior of any given black box model through joint optimization of unambiguity, fidelity, and interpretability, while also allowing users to explore model behavior based on their preferences. Experimental evaluation with real-world datasets and user studies demonstrates that our approach can generate highly compact, easy-to-understand, yet accurate approximations of various kinds of predictive models compared to state-of-the-art baselines.