# Explanation Shift: Detecting distribution shifts on tabular data via the explanation space

arXiv: https://arxiv.org/abs/2210.12369 · HTML: https://mlsanity.com/paper/2210.12369/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 22 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [On the Importance of Gradients for Detecting Distributional Shifts in the Wild](https://mlsanity.com/paper/2110.00218/) (2021)
- [Exploring the Limits of Out-of-Distribution Detection](https://mlsanity.com/paper/2106.03004/) (2021)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Why do tree-based models still outperform deep learning on tabular data?](https://mlsanity.com/paper/2207.08815/) (2022)
- [Leveraging Unlabeled Data to Predict Out-of-Distribution Performance](https://mlsanity.com/paper/2201.04234/) (2022)
- [Explaining Explanations in AI](https://mlsanity.com/paper/1811.01439/) (2018)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [A Unified View of Label Shift Estimation](https://mlsanity.com/paper/2003.07554/) (2020)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Explainable AI for Trees: From Local Explanations to Global Understanding](https://mlsanity.com/paper/1905.04610/) (2019)
- [Do We Really Need Deep Learning Models for Time Series Forecasting?](https://mlsanity.com/paper/2101.02118/) (2021)
- [Continual Learning in Practice](https://mlsanity.com/paper/1903.05202/) (2019)
- [Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection](https://mlsanity.com/paper/2110.14019/) (2021)
- [RATT: Leveraging Unlabeled Data to Guarantee Generalization](https://mlsanity.com/paper/2105.00303/) (2021)
- [Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap](https://mlsanity.com/paper/2201.11676/) (2022)

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

- [The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research](https://mlsanity.com/paper/2310.07882/) (2023)
- [Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance](https://mlsanity.com/paper/2408.13648/) (2024)
- [Beyond Demographic Parity: Redefining Equal Treatment](https://mlsanity.com/paper/2303.08040/) (2023)
- [Root Causing Prediction Anomalies Using Explainable AI](https://mlsanity.com/paper/2403.02439/) (2024)
- [Delta-Audit: Explaining What Changes When Models Change](https://mlsanity.com/paper/2508.19589/) (2025)
- [ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values](https://mlsanity.com/paper/2604.11200/) (2026)
- [Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs](https://mlsanity.com/paper/2610.16534/) (2026)

## Abstract (arXiv)

As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In the past, predictive performance was considered the key indicator to monitor. However, explanation aspects have come to attention within the last years. In this work, we investigate how model predictive performance and model explanation characteristics are affected under distribution shifts and how these key indicators are related to each other for tabular data. We find that the modeling of explanation shifts can be a better indicator for the detection of predictive performance changes than state-of-the-art techniques based on representations of distribution shifts. We provide a mathematical analysis of different types of distribution shifts as well as synthetic experimental examples.