mlsanityData to 14 Oct 2026

RHALE: Robust and Heterogeneity-aware Accumulated Local Effects

arXiv 2309.11193 ↗First posted 20 Sep 2023cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Accumulated Local Effects (ALE) is a widely-used explainability method for isolating the average effect of a feature on the output, because it handles cases with correlated features well. However, it has two limitations. First, it does not quantify the deviation of instance-level (local) effects from the average (global) effect, known as heterogeneity. Second, for estimating the average effect, it partitions the feature domain into user-defined, fixed-sized bins, where different bin sizes may lead to inconsistent ALE estimations. To address these limitations, we propose Robust and Heterogeneity-aware ALE (RHALE). RHALE quantifies the heterogeneity by considering the standard deviation of the local effects and automatically determines an optimal variable-size bin-splitting. In this paper, we prove that to achieve an unbiased approximation of the standard deviation of local effects within each bin, bin splitting must follow a set of sufficient conditions. Based on these conditions, we propose an algorithm that automatically determines the optimal partitioning, balancing the estimation bias and variance. Through evaluations on synthetic and real datasets, we demonstrate the superiority of RHALE compared to other methods, including the advantages of automatic bin splitting, especially in cases with correlated features.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 16 of its 24 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

16 of 24 references.

References · 16

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  4. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 285
  5. 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 213
  6. 2020Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challengescited by 120
  7. 2020General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Modelscited by 75
  8. 2018Visualizing the Feature Importance for Black Box Modelscited by 55
  9. 2018A Simple and Effective Model-Based Variable Importance Measurecited by 51
  10. 2020Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approachcited by 37
  11. 2021Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Processcited by 24
  12. 2022Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomenacited by 21
4 more
  1. 2022REPID: Regional Effect Plots with implicit Interaction Detectioncited by 17
  2. 2021Fooling Partial Dependence via Data Poisoningcited by 16
  3. 2019VINE: Visualizing Statistical Interactions in Black Box Modelscited by 13
  4. 2022DALE: Differential Accumulated Local Effects for efficient and accurate global explanationscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 4.

8 papers.

  1. 2023Regionally Additive Models: Explainable-by-design models minimizing feature interactionscited by 3
  2. 2023Statistical inference using machine learning and classical techniques based on accumulated local effects (ALE)cited by 3
  3. 2024On the Robustness of Global Feature Effect Explanationscited by 2
  4. 2024Effector: A Python package for regional explanationscited by 1
  5. 2026Analyzing Error Sources in Global Feature Effect Estimationcited by 1
  6. 2026Neural Additive Experts: Context-Gated Experts for Controllable Model Additivitycited by 0
  7. 2026Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effectscited by 0
  8. 2026SAILS: Surrogate-based Analysis of Interactions via Local Effect Smoothscited by 0