Saved in:
Bibliographic Details
Main Authors: Cheng, Chen, Li, Ang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.20176
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations, implicitly assuming that invariance implies reliability. However, features that are invariant across domains are not necessarily causally effective for prediction. In this work, we revisit OOD classification from a causal perspective and propose to evaluate learned representations based on their necessity and sufficiency under distribution shift. We introduce an explicit segment-level framework that directly measures causal effectiveness across domains, providing a more faithful criterion than invariance alone. Experiments on multi-domain benchmarks demonstrate consistent improvements in OOD performance, particularly under challenging domain shifts, highlighting the value of causal evaluation for robust generalization.