BELLA: Black box model Explanations by Local Linear Approximations
Not on the map. Why?
Abstract (arXiv)
Understanding the decision-making process of black-box models has become not just a legal requirement, but also an additional way to assess their performance. However, the state of the art post-hoc explanation approaches for regression models rely on synthetic data generation, which introduces uncertainty and can hurt the reliability of the explanations. Furthermore, they tend to produce explanations that apply to only very few data points. In this paper, we present BELLA, a deterministic model-agnostic post-hoc approach for explaining the individual predictions of regression black-box models. BELLA provides explanations in the form of a linear model trained in the feature space. BELLA maximizes the size of the neighborhood to which the linear model applies so that the explanations are accurate, simple, general, and robust.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 68 references that are in the map. First posted on arXiv 18 May 2023.
Builds on
31 of 68 references.
References · 31
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
- 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
- 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
- 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
- 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
- 2018On the Robustness of Interpretability Methodscited by 310
- 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
- 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
- 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
19 more
- 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
- 2018Abduction-Based Explanations for Machine Learning Modelscited by 159
- 2020Multi-Objective Counterfactual Explanationscited by 157
- 2018Model Agnostic Supervised Local Explanationscited by 83
- 2018Contrastive Explanation: A Structural-Model Approachcited by 64
- 2019DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systemscited by 59
- 2020PMLB v1.0: An open source dataset collection for benchmarking machine learning methodscited by 58
- 2019Measurable Counterfactual Local Explanations for Any Classifiercited by 48
- 2017Interpreting Blackbox Models via Model Extractioncited by 43
- 2018Stop Explaining Black Box Machine Learning Models for High Stakes Decisions and Use Interpretable Models Insteadcited by 40
- 2019Explaining a black-box using Deep Variational Information Bottleneck Approachcited by 35
- 2020A Framework to Learn with Interpretationcited by 23
- 2022Counterfactual Plans under Distributional Ambiguitycited by 19
- 2020Flexible and Context-Specific AI Explainability: A Multidisciplinary Approachcited by 13
- 2022Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanationscited by 11
- 2021AcME -- Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Boxcited by 8
- 2021MCCE: Monte Carlo sampling of realistic counterfactual explanationscited by 7
- 2022A Functional Information Perspective on Model Interpretationcited by 5
- 2022An Additive Instance-Wise Approach to Multi-class Model Interpretationcited by 3
Built on by
Not cited yet.