Towards Explaining Distribution Shifts

Sean Kulinski, David I. Inouye

Keywords: Distribution Shifts, Explainable AI

Abstract: Distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing the accuracy of downstream models. Thus, understanding such distribution shifts is critical for examining and hopefully mitigating the effect of such a shift. Most prior work has focused on merely detecting if a shift has occurred and assumes any detected shift can be understood and handled appropriately by a human operator. We hope to aid in these manual mitigation tasks by explaining the distribution shift using interpretable transportation maps from the original distribution to the shifted one. We derive our interpretable mappings from a relaxation of the optimal transport problem, where the candidate mappings are restricted to belong to a set of interpretable mappings. We then use quintessential examples of distribution shift in simulated and real-world cases to showcase how our explanatory mappings provide a better balance between detail and interpretability than the de facto standard mean shift explanation by both visual inspection and our PercentExplained metric.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)

TL;DR: We use interpretable distributional mappings to explain how a source distribution shifted to a target distribution, usable on both tabular and image-based distribution shifts.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2210.10275/code)