English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Despite impressive success in many tasks, deep learning models are shown torely on spurious features, which will catastrophically fail when generalized toout-of-distribution (OOD) data. Invariant Risk Minimization (IRM) is proposedto alleviate this issue by extracting domain-invariant features for OODgeneralization. Nevertheless, recent work shows that IRM is only effective fora certain type of distribution shift (e.g., correlation shift) while it failsfor other cases (e.g., diversity shift). Meanwhile, another thread of method,Adversarial Training (AT), has shown better domain transfer performance,suggesting that it has the potential to be an effective candidate forextracting domain-invariant features. This paper investigates this possibilityby exploring the similarity between the IRM and AT objectives. Inspired by thisconnection, we propose Domainwise Adversarial Training (DAT), an AT-inspiredmethod for alleviating distribution shift by domain-specific perturbations.Extensive experiments show that our proposed DAT can effectively removedomain-varying features and improve OOD generalization under both correlationshift and diversity shift.

On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization