Invariant Learning with Annotation-free Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913802949230592 |
|---|---|
| author | Le, Phuong Quynh Seifert, Christin Schlötterer, Jörg |
| author_facet | Le, Phuong Quynh Seifert, Christin Schlötterer, Jörg |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15686 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Invariant Learning with Annotation-free Environments Le, Phuong Quynh Seifert, Christin Schlötterer, Jörg Machine Learning 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. |
| title | Invariant Learning with Annotation-free Environments |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.15686 |