Tackling the XAI Disagreement Problem with Regional Explanations
G Laberge, YB Pequignot… - International …, 2024 - proceedings.mlr.press
Abstract The XAI Disagreement Problem concerns the fact that various explainability
methods yield different local/global insights on model behavior. Thus, given the lack of …
methods yield different local/global insights on model behavior. Thus, given the lack of …
Decomposing global feature effects based on feature interactions
Global feature effect methods, such as partial dependence plots, provide an intelligible
visualization of the expected marginal feature effect. However, such global feature effect …
visualization of the expected marginal feature effect. However, such global feature effect …
Rhale: Robust and heterogeneity-aware accumulated local effects
Abstract 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 …
the average effect of a feature on the output, because it handles cases with correlated …
On the Robustness of Global Feature Effect Explanations
We study the robustness of global post-hoc explanations for predictive models trained on
tabular data. Effects of predictor features in black-box supervised learning are an essential …
tabular data. Effects of predictor features in black-box supervised learning are an essential …
Interaction Difference Hypothesis Test for Prediction Models
T Welchowski, D Edelmann - Machine Learning and Knowledge …, 2024 - mdpi.com
Machine learning research focuses on the improvement of prediction performance. Progress
was made with black-box models that flexibly adapt to the given data. However, due to their …
was made with black-box models that flexibly adapt to the given data. However, due to their …
iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios
Post-hoc explanation techniques such as the well-established partial dependence plot
(PDP), which investigates feature dependencies, are used in explainable artificial …
(PDP), which investigates feature dependencies, are used in explainable artificial …
Regionally Additive Models: Explainable-by-design models minimizing feature interactions
Generalized Additive Models (GAMs) are widely used explainable-by-design models in
various applications. GAMs assume that the output can be represented as a sum of …
various applications. GAMs assume that the output can be represented as a sum of …
Leveraging Model-Based Trees as Interpretable Surrogate Models for Model Distillation
Surrogate models play a crucial role in retrospectively interpreting complex and powerful
black box machine learning models via model distillation. This paper focuses on using …
black box machine learning models via model distillation. This paper focuses on using …
Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots
The adoption of artificial intelligence (AI) across industries has led to the widespread use of
complex black-box models and interpretation tools for decision making. This paper proposes …
complex black-box models and interpretation tools for decision making. This paper proposes …
[PDF][PDF] Fast and Accurate Regional Effect Plots for Automated Tabular Data Analysis
V Gkolemis, T Dalamagas… - Proceedings of the … - tabular-data-analysis.github.io
Regional effect is a novel explainability method that can be used for automated tabular data
understanding through a three-step procedure; a black-box machine learning (ML) model is …
understanding through a three-step procedure; a black-box machine learning (ML) model is …