mlsanityData to 14 Oct 2026

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

arXiv 2210.12369 ↗First posted 22 Oct 2022cs.LG cs.AI stat.MLcited by 7

Not on the map. Why?

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.

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

23 of 34 references.

References · 23

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  3. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  6. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  7. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  8. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  9. 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 243
  10. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
  11. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 199
  12. 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performancecited by 145
11 more
  1. 2018Explaining Explanations in AIcited by 137
  2. 2020True to the Model or True to the Data?cited by 126
  3. 2020A Unified View of Label Shift Estimationcited by 119
  4. 2022Algorithms to estimate Shapley value feature attributionscited by 115
  5. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  6. 2019Explainable AI for Trees: From Local Explanations to Global Understandingcited by 65
  7. 2021Do We Really Need Deep Learning Models for Time Series Forecasting?cited by 45
  8. 2019Continual Learning in Practicecited by 28
  9. 2021Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detectioncited by 21
  10. 2021RATT: Leveraging Unlabeled Data to Guarantee Generalizationcited by 20
  11. 2022Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrapcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 2.

7 papers.

  1. 2023The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Researchcited by 4
  2. 2024Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performancecited by 4
  3. 2023Beyond Demographic Parity: Redefining Equal Treatmentcited by 3
  4. 2024Root Causing Prediction Anomalies Using Explainable AIcited by 0
  5. 2025Delta-Audit: Explaining What Changes When Models Changecited by 0
  6. 2026ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Valuescited by 0
  7. 2026Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphscited by 0