AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Coupled Training with Privileged Information and Unlabeled Data

Jiahao Shi, Omar Hagrass, Jason Matthew Klusowski

ICML 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Extrapolation and single-sample adaptation · 0 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
couple deployment and rich-view models in joint training instead of Two-Stage pseudo-labelingCoupled Training (random forest) · Parkinson's Telemonitoringtest MSE: 83.32 -> 72.60Improved
Two-Stage pseudo-labeling with privileged features versus X-only supervised baseline (ablation)Two-Stage · Parkinson's Telemonitoringtest MSE: 77.34 -> 83.32Hurt
couple deployment and rich-view models instead of X-only baselineCoupled Training (linear) · Bank Marketing, 26 seedsBrier score: 0.0893 -> 0.0881Improved
Two-Stage pseudo-labeling with corrupted privileged features versus X-only baseline (ablation)Two-Stage · Bank Marketing, 26 seedsBrier score: 0.0893 -> 0.0928Hurt
use squared-loss generalized distillation instead of Two-Stage (ablation)Two-Stage · Bank Marketing, 26 seedsBrier score: 0.0928 -> 0.0907Improved
use SVM+ (labeled-only privileged information) instead of X-only baseline (ablation)SVM+ · Bank Marketing, 26 seedsBrier score: 0.0893 -> 0.1470Hurt
increase coupling weight lambda from small to intermediate (ablation)Coupled Training · Parkinson's Telemonitoringtest MSEMixed
large lambda (approaches Two-Stage) versus intermediate lambda (ablation)Coupled Training (logistic) · synthetic classificationtest errorHurt
add small coupling when privileged signal is weak (aggressive pseudo-responses, small nu) (ablation)Coupled/Two-Stage regime · synthetic linear Gaussian, weak privileged signalestimation errorHurt
increase number of unlabeled samples (ablation)Coupled Training · synthetic linear controlstest errorImproved
increase nuisance privileged dimensions (ablation)Coupled Training vs Two-Stage · synthetic linear controlstest errorMixed
use AFS-based dictionary selection with intermediate lambdaCoupled Training with AFS · PneumoniaMNIST (n=100 labeled, 2000 unlabeled)test AUROCImproved

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