# Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations

arXiv: https://arxiv.org/abs/2603.14894 · HTML: https://mlsanity.com/paper/2603.14894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [Getting a CLUE: A Method for Explaining Uncertainty Estimates](https://mlsanity.com/paper/2006.06848/) (2020)
- [BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2012.03058/) (2020)
- [Rethinking Aleatoric and Epistemic Uncertainty](https://mlsanity.com/paper/2412.20892/) (2024)
- [GLIME: General, Stable and Local LIME Explanation](https://mlsanity.com/paper/2311.15722/) (2023)
- [Explaining Bayesian Neural Networks](https://mlsanity.com/paper/2108.10346/) (2021)
- [Calibrated Explanations: with Uncertainty Information and Counterfactuals](https://mlsanity.com/paper/2305.02305/) (2023)
- [Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainability](https://mlsanity.com/paper/2108.06907/) (2021)
- [Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals](https://mlsanity.com/paper/2505.13118/) (2025)
- [Making Things Explainable vs Explaining: Requirements and Challenges under the GDPR](https://mlsanity.com/paper/2110.00758/) (2021)
- [CLIMAX: An exploration of Classifier-Based Contrastive Explanations](https://mlsanity.com/paper/2307.00680/) (2023)
- [Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models](https://mlsanity.com/paper/2410.21129/) (2024)

## Abstract (arXiv)

Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge by learning a surrogate model that approximates the behavior of the deployed black-box ML model in the locality of a sample of interest. In post-hoc scenarios, neither the underlying model parameters nor the training are available, and hence, this local neighborhood must be constructed by generating perturbed inputs in the neighborhood of the sample of interest, and its corresponding model predictions. We propose Expected Active Gain for Local Explanations (textttEAGLE), a post-hoc model-agnostic explanation framework that formulates perturbation selection as an information-theoretic active learning problem. By adaptively sampling perturbations that maximize the expected information gain, textttEAGLE efficiently learns a linear surrogate explainable model while producing feature importance scores along with the uncertainty/confidence estimates. Theoretically, we establish that cumulative information gain scales as O(d log t), where d is the feature dimension and t represents the number of samples, and that the sample complexity grows linearly with d and logarithmically with the confidence parameter 1/δ. Empirical results on tabular and image datasets corroborate our theoretical findings and demonstrate that textttEAGLE improves explanation reproducibility across runs, achieves higher neighborhood stability, and improves perturbation sample quality as compared to state-of-the-art baselines such as Tilia, US-LIME, GLIME and BayesLIME.