# Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective

arXiv: https://arxiv.org/abs/2404.13522 · HTML: https://mlsanity.com/paper/2404.13522/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 21 Apr 2024.

## Builds on (most cited first, 18 of 18)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Shapley explainability on the data manifold](https://mlsanity.com/paper/2006.01272/) (2020)
- [The Inadequacy of Shapley Values for Explainability](https://mlsanity.com/paper/2302.08160/) (2023)
- [Explaining black box decisions by Shapley cohort refinement](https://mlsanity.com/paper/1911.00467/) (2019)
- [On the Robustness of Removal-Based Feature Attributions](https://mlsanity.com/paper/2306.07462/) (2023)
- [Rational Shapley Values](https://mlsanity.com/paper/2106.10191/) (2021)
- [Explainable Machine Learning for Fraud Detection](https://mlsanity.com/paper/2105.06314/) (2021)
- [Manifold Restricted Interventional Shapley Values](https://mlsanity.com/paper/2301.04041/) (2023)
- [Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations](https://mlsanity.com/paper/2202.11919/) (2022)

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

- [A Comprehensive Study of Shapley Value in Data Analytics](https://mlsanity.com/paper/2412.01460/) (2024)

## Abstract (arXiv)

Shapley value attribution (SVA) is an increasingly popular explainable AI (XAI) method, which quantifies the contribution of each feature to the model's output. However, recent work has shown that most existing methods to implement SVAs have some drawbacks, resulting in biased or unreliable explanations that fail to correctly capture the true intrinsic relationships between features and model outputs. Moreover, the mechanism and consequences of these drawbacks have not been discussed systematically. In this paper, we propose a novel error theoretical analysis framework, in which the explanation errors of SVAs are decomposed into two components: observation bias and structural bias. We further clarify the underlying causes of these two biases and demonstrate that there is a trade-off between them. Based on this error analysis framework, we develop two novel concepts: over-informative and underinformative explanations. We demonstrate how these concepts can be effectively used to understand potential errors of existing SVA methods. In particular, for the widely deployed assumption-based SVAs, we find that they can easily be under-informative due to the distribution drift caused by distributional assumptions. We propose a measurement tool to quantify such a distribution drift. Finally, our experiments illustrate how different existing SVA methods can be over- or under-informative. Our work sheds light on how errors incur in the estimation of SVAs and encourages new less error-prone methods.