Interpretable Distribution Shift Detection using Optimal Transport

08/04/2022
by   Neha Hulkund, et al.
29

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.

READ FULL TEXT
research
10/19/2022

Towards Explaining Distribution Shifts

A distribution shift can have fundamental consequences such as signaling...
research
04/18/2021

Failing Conceptually: Concept-Based Explanations of Dataset Shift

Despite their remarkable performance on a wide range of visual tasks, ma...
research
05/25/2023

Characterizing Out-of-Distribution Error via Optimal Transport

Out-of-distribution (OOD) data poses serious challenges in deployed mach...
research
01/05/2022

Frame Shift Prediction

Frame shift is a cross-linguistic phenomenon in translation which result...
research
08/11/2022

Optimal Transport Features for Morphometric Population Analysis

Brain pathologies often manifest as partial or complete loss of tissue. ...
research
06/30/2022

AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection

Analyzing the distribution shift of data is a growing research direction...
research
12/21/2020

Making transport more robust and interpretable by moving data through a small number of anchor points

Optimal transport (OT) is a widely used technique for distribution align...

Please sign up or login with your details

Forgot password? Click here to reset