Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features

Document Type

Conference Proceeding

Publication Title

Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022

Abstract

Machine learning has demonstrated remarkable prediction accuracy over i.i.d data, but the accuracy often drops when tested with data from another distribution. In this paper, we aim to offer another view of this problem in a perspective assuming the reason behind this accuracy drop is the reliance of models on the features that are not aligned well with how a data annotator considers similar across these two datasets. We refer to these features as misaligned features. We extend the conventional generalization error bound to a new one for this setup with the knowledge of how the misaligned features are associated with the label. Our analysis offers a set of techniques for this problem, and these techniques are naturally linked to many previous methods in robust machine learning literature. We also compared the empirical strength of these methods demonstrated the performance when these previous techniques are combined, with implementation available here.

First Page

2075

Last Page

2084

Publication Date

2-28-2022

Keywords

robustness, human-aligned, domain adaptation, data-oriented learning

Comments

IR conditions: non-described

Share

COinS