Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features
This work addresses cross-domain robustness for machine learning models, but it is incremental as it builds on and combines previous techniques without introducing a fundamentally new approach.
The paper tackles the problem of model accuracy dropping on out-of-distribution data by attributing it to reliance on misaligned features, and proposes techniques derived from a new generalization error bound that combine existing methods to improve robustness.
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 an implementation available at https://github.com/OoDBag/WR