Invariant Learning with Annotation-free Environments

Phuong Quynh Le, Christin Seifert, Jörg Schlötterer

Abstract

Invariant learning is a promising approach to improve domain generalization compared to Empirical Risk Minimization (ERM). However, most invariant learning methods rely on the assumption that training examples are pre-partitioned into different known environments. We instead infer environments without the need for additional annotations, motivated by observations of the properties within the representation space of a trained ERM model. We show the preliminary effectiveness of our approach on the ColoredMNIST benchmark, achieving performance comparable to methods requiring explicit environment labels and on par with an annotation-free method that poses strong restrictions on the ERM reference model.
BibTeX
@misc{le2024invariant,
  author = {Phuong Quynh Le and Christin Seifert and Jörg Schlötterer},
  title = {{Invariant Learning with Annotation-free Environments}},
  year = {2024},
  eprint = {2504.15686},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.15686},
}
Figure