# Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection

arXiv: https://arxiv.org/abs/2312.12115 · HTML: https://mlsanity.com/paper/2312.12115/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 7 of 7)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [s-LIME: Reconciling Locality and Fidelity in Linear Explanations](https://mlsanity.com/paper/2208.01510/) (2022)

## Built on by (most cited first, 7 of 7)

- [PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression](https://mlsanity.com/paper/2601.18608/) (2026)
- [Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution](https://mlsanity.com/paper/2404.01078/) (2024)
- [Explaining Deep Learning-based Anomaly Detection in Energy Consumption Data by Focusing on Contextually Relevant Data](https://mlsanity.com/paper/2501.06099/) (2025)
- [Top-k Feature Importance Ranking](https://mlsanity.com/paper/2509.15420/) (2025)
- [ColonScopeX: Leveraging Explainable Expert Systems with Multimodal Data for Improved Early Diagnosis of Colorectal Cancer](https://mlsanity.com/paper/2504.08824/) (2025)
- [LEMON: Local Explanations via Modality-aware OptimizatioN](https://mlsanity.com/paper/2602.02786/) (2026)
- [NEURON: A Neuro-symbolic System for Grounded Clinical Explainability](https://mlsanity.com/paper/2605.01189/) (2026)

## Abstract (arXiv)

Machine learning techniques, such as deep learning and ensemble methods, are widely used in various domains due to their ability to handle complex real-world tasks. However, their black-box nature has raised multiple concerns about the fairness, trustworthiness, and transparency of computer-assisted decision-making. This has led to the emergence of local post-hoc explainability methods, which offer explanations for individual decisions made by black-box algorithms. Among these methods, Kernel SHAP is widely used due to its model-agnostic nature and its well-founded theoretical framework. Despite these strengths, Kernel SHAP suffers from high instability: different executions of the method with the same inputs can lead to significantly different explanations, which diminishes the relevance of the explanations. The contribution of this paper is two-fold. On the one hand, we show that Kernel SHAP's instability is caused by its stochastic neighbor selection procedure, which we adapt to achieve full stability without compromising explanation fidelity. On the other hand, we show that by restricting the neighbors generation to perturbations of size 1 -- which we call the coalitions of Layer 1 -- we obtain a novel feature-attribution method that is fully stable, computationally efficient, and still meaningful.