A Bayesian explanation of machine learning models based on modes and functional ANOVA

Quan Long
11/5/2024
cs.LGcs.AIstat.CO

No confident code implementation found for this paper.

Abstract

Most methods in explainable AI (XAI) focus on providing reasons for the prediction of a given set of features. However, we solve an inverse explanation problem, i.e., given the deviation of a label, find the reasons of this deviation. We use a Bayesian framework to recover the ``true'' features, conditioned on the observed label value. We efficiently explain the deviation of a label value from the mode, by identifying and ranking the influential features using the ``distances'' in the ANOVA functional decomposition. We show that the new method is more human-intuitive and robust than methods based on mean values, e.g., SHapley Additive exPlanations (SHAP values). The extra costs of solving a Bayesian inverse problem are dimension-independent.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Achieving interpretable machine learning by functional decomposition of black-box models into explainable predictor effects

82% match2024

Unified Explanations in Machine Learning Models: A Perturbation Approach

81% match1 repo2024

LAVA: Explainability for Unsupervised Latent Embeddings

81% match2025

Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception

81% match2025

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability

81% match2026

Position: Rethinking Explainable Machine Learning as Applied Statistics

80% match2026

Cite this paper

@article{long2024bayesian,
  title  = {A Bayesian explanation of machine learning models based on modes and functional ANOVA},
  author = {Quan Long},
  year   = {2024},
  eprint = {2411.02746},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.02746v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.02746.svg)](https://codeofpaper.com/paper/2411.02746)

Discussion