AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness

Subeen Park, JOOWANG KIM, Hakyung Lee, Sunjae yoo, Kyungwoo Song

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add embedding regularization (SCER) to worst-group trainingResNet-50 on Waterbirds · Waterbirdsworst-group accuracy: 90.3 -> 91.2 (vs PDE); ERM 69.1Improved
add SCERResNet-50 on CelebA · CelebAworst-group accuracy: 91.4 -> 91.4 (vs ElRep)No clear effect
add SCERResNet-50 on ColorMNIST (rho=80%) · ColorMNIST (rho=80%)worst-group accuracy: 73.2 -> 73.6 (vs LISA)No clear effect
add SCERResNet-50 on ColorMNIST (rho=99%) · ColorMNIST (rho=99%)worst-group accuracy: 47.5 -> 56.0 (vs PDE)Improved
add SCER when one subpopulation is absent from trainingResNet-50 on ColorMNIST · ColorMNIST (one subpopulation omitted)worst-group accuracy: 44.1 -> 59.6 (vs GroupDRO)Improved
use SCER as second stage after EIIL environment inferenceColorMNIST · ColorMNIST (two train envs)average accuracy: 68.2 -> 72.6 (vs EIIL + DRO)Improved
add SCER to BERTBERT on CivilComments · CivilCommentsworst-group accuracy: 73.7 -> 74.0 (vs LISA)No clear effect
add SCERBERT on MultiNLI · MultiNLIworst-group accuracy: 76.0 -> 76.8 (vs GroupDRO)Improved
add core and spurious embedding losses (ablation)SCER · ColorMNIST (rho=95%)worst-group accuracy: 70.7 -> 72.8Improved
add core loss alone (lambda_core 0.5) (ablation)SCER · ColorMNIST (rho=95%)worst-group accuracy: 71.6 -> 72.2Improved
increase spurious loss weight from 0.5 to 1.0 (ablation)SCER · ColorMNIST (rho=95%)worst-group accuracy: 71.6 -> 72.8Improved
use Sigma-norm (covariance-based) instead of Euclidean norm (ablation)SCER · ColorMNIST (rho=95%)worst-group accuracy: 70.0 -> 72.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy