Interpretable Distribution Shift Detection using Optimal Transport

TL;DR

This paper introduces an optimal transport-based method for detecting and interpreting distribution shifts in classification datasets, enabling class-specific analysis and sample retrieval for better understanding of dataset changes.

Contribution

It presents a novel, interpretable approach to identify and analyze distribution shifts using optimal transport, with class-specific insights and sample retrieval capabilities.

Findings

Effective identification of distribution shifts in synthetic and real datasets

Ability to determine which classes are affected by shifts

Retrieval of sample pairs for interpretability

Abstract

We propose a method to identify and characterize distribution shifts in classification datasets based on optimal transport. It allows the user to identify the extent to which each class is affected by the shift, and retrieves corresponding pairs of samples to provide insights on its nature. We illustrate its use on synthetic and natural shift examples. While the results we present are preliminary, we hope that this inspires future work on interpretable methods for analyzing distribution shifts.