Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
Name
vendrow-jvendrow-sm-eecs-2024-thesis.pdf
Description
Thesis PDF
Size
44.71 MB
Format
Adobe PDF
Checksum (MD5)
6a760e0b195a9bd95281a6a103ffda51
Author(s)
Vendrow, Joshua L.
Advisor(s)
Mądry, Aleksander
Date Issued
May 2024
Publisher
Massachusetts Institute of Technology
Abstract
Distribution shift is a major source of failure for machine learning models. However, evaluating model reliability under distribution shift can be challenging, especially since it may be difficult to acquire counterfactual examples that exhibit a specified shift. In this work, we introduce the notion of a dataset interface: a framework that, given an input dataset and a user-specified shift, returns instances from that input distribution that exhibit the desired shift. We study a number of natural implementations for such an interface, and find that they often introduce confounding shifts that complicate model evaluation. Motivated by this, we propose a dataset interface implementation that leverages Textual Inversion to tailor generation to the input distribution.
We then demonstrate how applying this dataset interface to the ImageNet dataset enables studying model behavior across a diverse array of distribution shifts, including variations in background, lighting, and attributes of the objects.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
