Lune

AAAI2025Top-tier venue

Conditional Feature Importance with Generative Modeling Using Adversarial Random Forests

Kristin Blesch, Niklas Koenen, Jan Kapar, Pegah Golchian, Lukas Burk, Markus Loecher, Marvin N. Wright

Abstract

This paper proposes a method for measuring conditional feature importance via generative modeling. In explainable artificial intelligence (XAI), conditional feature importance assesses the impact of a feature on a prediction model's performance given the information of other features. Model-agnostic post hoc methods to do so typically evaluate changes in the predictive performance under on-manifold feature value manipulations. Such procedures require creating feature values that respect conditional feature distributions, which can be challenging in practice. Recent advancements in generative modeling can facilitate this. For tabular data, which may consist of both categorical and continuous features, the adversarial random forest (ARF) stands out as a generative model that can generate on-manifold data points without requiring intensive tuning efforts or computational resources, making it a promising candidate model for subroutines in XAI methods. This paper proposes cARFi (conditional ARF feature importance), a method for measuring conditional feature importance through feature values sampled from ARF-estimated conditional distributions. cARFi requires only little tuning to yield robust importance scores that can flexibly adapt for conditional or marginal notions of feature importance, including straightforward extensions to condition on feature subsets and allows for inferring the significance of feature importances through statistical tests.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. Understanding Global Feature Contributions With Additive Importance MeasuresIan Covert, Scott M. Lundberg, Su-In LeeNeurIPS 2020 · 476 citations
  3. Joints in Random ForestsAlvaro H. C. Correia, Robert Peharz, Cassio P. de CamposNeurIPS 2020 · 44 citations

Related papers

  1. FIMAP: Feature Importance by Minimal Adversarial PerturbationMatt Chapman-Rounds, Umang Bhatt, Erik Pazos, Marc-Andre Schulz et al.AAAI 2021 · 14 citations
  2. DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible ControlOleksii Furman, Ulvi Movsum-zada, Patryk Marszalek, Maciej Zieba et al.NeurIPS 2025 · 3 citations
  3. Accurate Estimation of Feature Importance Faithfulness for Tree ModelsMateusz Gajewski, Adam Karczmarz, Mateusz Rapicki, Piotr SankowskiAAAI 2025
  4. Theoretical Behavior of XAI Methods in the Presence of Suppressor VariablesRick Wilming, Leo Kieslich, Benedict Clark, Stefan HaufeICML 2023 · 17 citations
  5. Label-Free Explainability for Unsupervised ModelsJonathan Crabbé, Mihaela van der SchaarICML 2022 · 24 citations
Dusk over the sea between two cliffs drawn in fine vertical lines