Year: 2025
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Le, Phuong Quynh, Seifert, Christin, Schlötterer, Jörg
Institutions: Philipps University of Marburg, University of Mannheim
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414632075
Cites:
Cited by:
Related to: