AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Environment Inference for Invariant Learning

Elliot Creager, Joern-Henrik Jacobsen, Richard Zemel

ICML 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 52 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
Infer environments from aggregated data and use IRM instead of handcrafted environmentsCMNIST invariant learning · CMNIST testaccuracy (%): 65.5 ± 2.3 -> 68.4 ± 2.7Improved
Infer environments and use GroupDRO rather than ERMWaterbirds · Waterbirds test (worst group)accuracy (%): 60.3 -> 78.7Improved
Infer environments and use GroupDRO rather than ERMWaterbirds · Waterbirds test (avg)accuracy (%): 97.3 -> 96.9Hurt
Infer environments and apply invariant learning rather than ERMAdult-Confounded · Adult-Confounded testaccuracy: 31.1 ± 4.4 -> 78.8 ± 1.4Improved
Infer environments using binning and apply GroupDRO rather than ERMCivilComments-WILDS · CivilComments-WILDS test (worst group)accuracy: 61.6 ± 1.3 -> 67.0 ± 2.4Improved
Infer environments using binning and apply GroupDRO rather than ERMCivilComments-WILDS · CivilComments-WILDS test (avg)accuracy: 92.0 ± 0.4 -> 90.5 ± 0.2Hurt
Use an ERM reference that learns the spurious color feature rather than a reference that does not expose the relevant biasEIIL on CMNIST · CMNISTgeneralizationMixed
Use a hand-coded color-based predictor as the reference modelEIIL on CMNIST · CMNISTgeneralizationImproved
Jointly train the classifier and environment assignments with alternating updates instead of the sequential two-stage procedure (ablation)EIIL · Experiments reported in the paperperformanceNo clear effect

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