Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Naumann, Philip, Kauffmann, Jacob, Montavon, Grégoire
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911474873532416
author Naumann, Philip
Kauffmann, Jacob
Montavon, Grégoire
author_facet Naumann, Philip
Kauffmann, Jacob
Montavon, Grégoire
contents Wasserstein distances provide a powerful framework for comparing data distributions. They can be used to analyze processes over time or to detect inhomogeneities within data. However, simply calculating the Wasserstein distance or analyzing the corresponding transport plan (or coupling) may not be sufficient for understanding what factors contribute to a high or low Wasserstein distance. In this work, we propose a novel solution based on Explainable AI that allows us to efficiently and accurately attribute Wasserstein distances to various data components, including data subgroups, input features, or interpretable subspaces. Our method achieves high accuracy across diverse datasets and Wasserstein distance specifications, and its practical utility is demonstrated in three use cases.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06123
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena
Naumann, Philip
Kauffmann, Jacob
Montavon, Grégoire
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Wasserstein distances provide a powerful framework for comparing data distributions. They can be used to analyze processes over time or to detect inhomogeneities within data. However, simply calculating the Wasserstein distance or analyzing the corresponding transport plan (or coupling) may not be sufficient for understanding what factors contribute to a high or low Wasserstein distance. In this work, we propose a novel solution based on Explainable AI that allows us to efficiently and accurately attribute Wasserstein distances to various data components, including data subgroups, input features, or interpretable subspaces. Our method achieves high accuracy across diverse datasets and Wasserstein distance specifications, and its practical utility is demonstrated in three use cases.
title Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.06123