mlsanityData to 14 Oct 2026

Confident Feature Ranking

arXiv 2307.15361 ↗First posted 28 Jul 2023stat.ML cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Machine learning models are widely applied in various fields. Stakeholders often use post-hoc feature importance methods to better understand the input features' contribution to the models' predictions. The interpretation of the importance values provided by these methods is frequently based on the relative order of the features (their ranking) rather than the importance values themselves. Since the order may be unstable, we present a framework for quantifying the uncertainty in global importance values. We propose a novel method for the post-hoc interpretation of feature importance values that is based on the framework and pairwise comparisons of the feature importance values. This method produces simultaneous confidence intervals for the features' ranks, which include the ``true'' (infinite sample) ranks with high probability, and enables the selection of the set of the top-k important features.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 20 of its 78 references that are in the map. First posted on arXiv 28 Jul 2023.

Builds on

20 of 78 references.

References · 20

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
  4. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 344
  5. 2018On the Robustness of Interpretability Methodscited by 314
  6. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  7. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  8. 2020General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Modelscited by 75
  9. 2019Explainable AI for Trees: From Local Explanations to Global Understandingcited by 65
  10. 2022Rethinking Stability for Attribution-based Explanationscited by 52
  11. 2018Stakeholders in Explainable AIcited by 48
  12. 2020Robust and Stable Black Box Explanationscited by 47
8 more
  1. 2021A Survey on the Robustness of Feature Importance and Counterfactual Explanationscited by 39
  2. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  3. 2021Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Processcited by 24
  4. 2020Understanding Global Feature Contributions With Additive Importance Measurescited by 10
  5. 2021Uncertainty in Rankingcited by 6
  6. 2021Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approachcited by 6
  7. 2017An improvement of Tukey's HSD with application to ranking institutionscited by 5
  8. 2022Ranking with Confidence for Large Scale Comparison Datacited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 2.

6 papers.

  1. 2024Prediction-Powered Ranking of Large Language Modelscited by 29
  2. 2024Feature Responsiveness Scores: Model-Agnostic Explanations for Recoursecited by 8
  3. 2024Statistical Significance of Feature Importance Rankingscited by 7
  4. 2026Quantifying Ranking Uncertainty in LLM Benchmarkscited by 2
  5. 2026Rank Confidence Sequences:Anytime-valid Leaderboardscited by 2
  6. 2025Top-k Feature Importance Rankingcited by 1