# Explainability of Machine Learning Models under Missing Data

arXiv: https://arxiv.org/abs/2407.00411 · HTML: https://mlsanity.com/paper/2407.00411/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 29 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- ["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)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares](https://mlsanity.com/paper/1410.2596/) (2014)
- [Graphical Models for Processing Missing Data](https://mlsanity.com/paper/1801.03583/) (2018)
- [Missing Data Imputation with Adversarially-trained Graph Convolutional Networks](https://mlsanity.com/paper/1905.01907/) (2019)
- [Shapley values for feature selection: The good, the bad, and the axioms](https://mlsanity.com/paper/2102.10936/) (2021)
- [Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Values](https://mlsanity.com/paper/2110.01307/) (2021)
- [MIDA: Multiple Imputation using Denoising Autoencoders](https://mlsanity.com/paper/1705.02737/) (2017)
- [Rational Shapley Values](https://mlsanity.com/paper/2106.10191/) (2021)
- [Polynomial Matrix Completion for Missing Data Imputation and Transductive Learning](https://mlsanity.com/paper/1912.06989/) (2019)
- [Multiple imputation for continuous variables using a Bayesian principal component analysis](https://mlsanity.com/paper/1401.5747/) (2014)
- [Multiple Imputation of Missing Categorical and Continuous Values via Bayesian Mixture Models with Local Dependence](https://mlsanity.com/paper/1410.0438/) (2014)
- [EPEM: Efficient Parameter Estimation for Multiple Class Monotone Missing Data](https://mlsanity.com/paper/2009.11360/) (2020)
- [Robust training of recurrent neural networks to handle missing data for disease progression modeling](https://mlsanity.com/paper/1808.05500/) (2018)
- [Gaussian Processes for Missing Value Imputation](https://mlsanity.com/paper/2204.04648/) (2022)
- [Correlation visualization under missing values: a comparison between imputation and direct parameter estimation methods](https://mlsanity.com/paper/2305.06044/) (2023)
- [Explainable Data Imputation using Constraints](https://mlsanity.com/paper/2205.04731/) (2022)

## Built on by (most cited first, 5 of 5)

- [Common Steps in Machine Learning Might Hinder The Explainability Aims in Medicine](https://mlsanity.com/paper/2409.00155/) (2024)
- [Missingness Bias Calibration in Feature Attribution Explanations](https://mlsanity.com/paper/2603.04831/) (2026)
- [Imputation Uncertainty in Interpretable Machine Learning Methods](https://mlsanity.com/paper/2512.17689/) (2025)
- [Evaluating Counterfactual Explanation Methods on Incomplete Inputs](https://mlsanity.com/paper/2604.08004/) (2026)
- [Shapley Value Estimation for Multi-Site Data with Blockwise-Missing Features](https://mlsanity.com/paper/2609.14902/) (2026)

## Abstract (arXiv)

Missing data is a prevalent issue that can significantly impair model performance and explainability. This paper briefly summarizes the development of the field of missing data with respect to Explainable Artificial Intelligence and experimentally investigates the effects of various imputation methods on SHAP (SHapley Additive exPlanations), a popular technique for explaining the output of complex machine learning models. Next, we compare different imputation strategies and assess their impact on feature importance and interaction as determined by Shapley values. Moreover, we also theoretically analyze the effects of missing values on Shapley values. Importantly, our findings reveal that the choice of imputation method can introduce biases that could lead to changes in the Shapley values, thereby affecting the explainability of the model. Moreover, we also show that a lower test prediction MSE (Mean Square Error) does not necessarily imply a lower MSE in Shapley values and vice versa. Also, while XGBoost (eXtreme Gradient Boosting) is a method that could handle missing data directly, using XGBoost directly on missing data can seriously affect explainability compared to imputing the data before training XGBoost. This study provides a comprehensive evaluation of imputation methods in the context of model explanations, offering practical guidance for selecting appropriate techniques based on dataset characteristics and analysis objectives. The results underscore the importance of considering imputation effects to ensure robust and reliable insights from machine learning models.