# Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach

arXiv: https://arxiv.org/abs/2111.09121 · HTML: https://mlsanity.com/paper/2111.09121/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 17 Nov 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques](https://mlsanity.com/paper/1909.03012/) (2019)
- [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)
- [Explaining the Explainer: A First Theoretical Analysis of LIME](https://mlsanity.com/paper/2001.03447/) (2020)
- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [bLIMEy: Surrogate Prediction Explanations Beyond LIME](https://mlsanity.com/paper/1910.13016/) (2019)
- [Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series](https://mlsanity.com/paper/2010.11310/) (2020)
- [Aggregating explanation methods for stable and robust explainability](https://mlsanity.com/paper/1903.00519/) (2019)
- [Towards Aggregating Weighted Feature Attributions](https://mlsanity.com/paper/1901.10040/) (2019)
- [Understanding surrogate explanations: the interplay between complexity, fidelity and coverage](https://mlsanity.com/paper/2107.04309/) (2021)
- [On the overlooked issue of defining explanation objectives for local-surrogate explainers](https://mlsanity.com/paper/2106.05810/) (2021)
- [Explainers in the Wild: Making Surrogate Explainers Robust to Distortions through Perception](https://mlsanity.com/paper/2102.10951/) (2021)

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

- [Boundary-Aware Uncertainty for Feature Attribution Explainers](https://mlsanity.com/paper/2210.02419/) (2022)
- [Confident Feature Ranking](https://mlsanity.com/paper/2307.15361/) (2023)
- [Uncertainty Quantification for Local Model Explanations Without Model Access](https://mlsanity.com/paper/2301.05761/) (2023)
- [REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability](https://mlsanity.com/paper/2412.08513/) (2024)
- [Uncertainty in Additive Feature Attribution methods](https://mlsanity.com/paper/2311.17446/) (2023)
- [Learning Conformal Explainers for Image Classifiers](https://mlsanity.com/paper/2509.21209/) (2025)

## Abstract (arXiv)

Explainability of black-box machine learning models is crucial, in particular when deployed in critical applications such as medicine or autonomous cars. Existing approaches produce explanations for the predictions of models, however, how to assess the quality and reliability of such explanations remains an open question. In this paper we take a step further in order to provide the practitioner with tools to judge the trustworthiness of an explanation. To this end, we produce estimates of the uncertainty of a given explanation by measuring the ordinal consensus amongst a set of diverse bootstrapped surrogate explainers. While we encourage diversity by using ensemble techniques, we propose and analyse metrics to aggregate the information contained within the set of explainers through a rating scheme. We empirically illustrate the properties of this approach through experiments on state-of-the-art Convolutional Neural Network ensembles. Furthermore, through tailored visualisations, we show specific examples of situations where uncertainty estimates offer concrete actionable insights to the user beyond those arising from standard surrogate explainers.