# Rethinking Stability for Attribution-based Explanations

arXiv: https://arxiv.org/abs/2203.06877 · HTML: https://mlsanity.com/paper/2203.06877/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 14 Mar 2022.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Explanations can be manipulated and geometry is to blame](https://mlsanity.com/paper/1906.07983/) (2019)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods](https://mlsanity.com/paper/2106.09078/) (2021)
- [From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence](https://mlsanity.com/paper/2104.13299/) (2021)

## Built on by (most cited first, 30 of 52)

- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)
- [TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations](https://mlsanity.com/paper/2207.04154/) (2022)
- [The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus](https://mlsanity.com/paper/2302.07265/) (2023)
- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Use-Case-Grounded Simulations for Explanation Evaluation](https://mlsanity.com/paper/2206.02256/) (2022)
- [Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics](https://mlsanity.com/paper/2409.16756/) (2024)
- [Efficient XAI Techniques: A Taxonomic Survey](https://mlsanity.com/paper/2302.03225/) (2023)
- [Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test](https://mlsanity.com/paper/2401.06465/) (2024)
- [A Fresh Look at Sanity Checks for Saliency Maps](https://mlsanity.com/paper/2405.02383/) (2024)
- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability](https://mlsanity.com/paper/2210.17376/) (2022)
- [Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance](https://mlsanity.com/paper/2502.04695/) (2025)
- [Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions](https://mlsanity.com/paper/2206.12481/) (2022)
- [Confident Feature Ranking](https://mlsanity.com/paper/2307.15361/) (2023)
- [From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition](https://mlsanity.com/paper/2402.12790/) (2024)
- [Provably Better Explanations with Optimized Aggregation of Feature Attributions](https://mlsanity.com/paper/2406.05090/) (2024)
- [FLEXtime: Filterbank learning to explain time series](https://mlsanity.com/paper/2411.05841/) (2024)
- [Rethinking Explainability in the Era of Multimodal AI](https://mlsanity.com/paper/2506.13060/) (2025)
- [GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs](https://mlsanity.com/paper/2507.18043/) (2025)
- [On the Robustness of Explanations of Deep Neural Network Models: A Survey](https://mlsanity.com/paper/2211.04780/) (2022)
- [The Blame Problem in Evaluating Local Explanations, and How to Tackle it](https://mlsanity.com/paper/2310.03466/) (2023)
- [Revisiting the robustness of post-hoc interpretability methods](https://mlsanity.com/paper/2407.19683/) (2024)
- [A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics](https://mlsanity.com/paper/2301.13445/) (2023)
- [Expected Grad-CAM: Towards gradient faithfulness](https://mlsanity.com/paper/2406.01274/) (2024)
- [Saliency strikes back: How filtering out high frequencies improves white-box explanations](https://mlsanity.com/paper/2307.09591/) (2023)
- [On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2507.05916/) (2025)
- [On the stability, correctness and plausibility of visual explanation methods based on feature importance](https://mlsanity.com/paper/2311.12860/) (2023)
- [Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures](https://mlsanity.com/paper/2411.03714/) (2024)
- [Uncertainty Quantification for Local Model Explanations Without Model Access](https://mlsanity.com/paper/2301.05761/) (2023)
- [Feature Importance Disparities for Data Bias Investigations](https://mlsanity.com/paper/2303.01704/) (2023)

## Abstract (arXiv)

As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are stable, e.g., robust to infinitesimal perturbations to an input. However, previous works have shown that state-of-the-art explanation methods generate unstable explanations. Here, we introduce metrics to quantify the stability of an explanation and show that several popular explanation methods are unstable. In particular, we propose new Relative Stability metrics that measure the change in output explanation with respect to change in input, model representation, or output of the underlying predictor. Finally, our experimental evaluation with three real-world datasets demonstrates interesting insights for seven explanation methods and different stability metrics.