Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Butler, Kurt, Feng, Guanchao, Djuric, Petar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911404434391040
author Butler, Kurt
Feng, Guanchao
Djuric, Petar
author_facet Butler, Kurt
Feng, Guanchao
Djuric, Petar
contents Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it becomes less clear when the predictive model involves interactions, such as multiplicative relationships or joint feature contributions. In this work, we propose a general theory of higher-order feature attribution, which we develop on the foundation of Integrated Gradients (IG). This work extends existing frameworks in the literature on explainable AI. When using IG as the method of feature attribution, we discover natural connections to statistics and topological signal processing. We provide several theoretical results that establish the theory, and we validate our theory on a few examples.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06165
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing
Butler, Kurt
Feng, Guanchao
Djuric, Petar
Machine Learning
Signal Processing
Statistics Theory
68Q32, 68T01
Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it becomes less clear when the predictive model involves interactions, such as multiplicative relationships or joint feature contributions. In this work, we propose a general theory of higher-order feature attribution, which we develop on the foundation of Integrated Gradients (IG). This work extends existing frameworks in the literature on explainable AI. When using IG as the method of feature attribution, we discover natural connections to statistics and topological signal processing. We provide several theoretical results that establish the theory, and we validate our theory on a few examples.
title Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing
topic Machine Learning
Signal Processing
Statistics Theory
68Q32, 68T01
url https://arxiv.org/abs/2510.06165