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

Researchers have developed a new Explainable AI method that makes Wasserstein distances more interpretable by attributing distance calculations to specific data components like subgroups and features. The framework enables better analysis of dataset shifts and transport phenomena across diverse applications with high accuracy.

• →New Explainable AI approach makes Wasserstein distance calculations more transparent and interpretable.
• →Method can attribute distance measurements to specific data subgroups, input features, or interpretable subspaces.
• →Framework achieves high accuracy across diverse datasets and various Wasserstein distance specifications.
• →Three practical use cases demonstrate the method's utility for analyzing data distribution changes over time.
• →Solution addresses limitations of simply calculating Wasserstein distances without understanding contributing factors.