# Alternative Methods to SHAP Derived from Properties of Kernels: A Note on Theoretical Analysis

arXiv: https://arxiv.org/abs/2406.00371 · HTML: https://mlsanity.com/paper/2406.00371/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 11 references that are in the map.
- First posted on arXiv 1 Jun 2024.

## Builds on (most cited first, 4 of 4)

- [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)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital](https://mlsanity.com/paper/2112.11071/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Polynomial-Time Axiomatic Alternative to SHAP for Feature Attribution](https://mlsanity.com/paper/2603.00496/) (2026)

## Abstract (arXiv)

This study first derives a general and analytical expression of AFA (Additive Feature Attribution) in terms of the kernel in LIME (Local Interpretable Model-agnostic Explanations). Then, we propose some new AFAs that have appropriate properties of kernels or that coincide with the LS prenucleolus in cooperative game theory. We also revisit existing AFAs such as SHAP (SHapley Additive exPlanations) and re-examine the properties of their kernels.