AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning

Hengwei Zhao, Zhengzhong Tu, Zhuo Zheng, Wei Wang, Junjue Wang, Rusty Feagin, Wenzhe Jiao

ICLR 2026 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 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
add NoiSNCL non-contrastive representation loss to label disambiguation (ablation)NcPU · CIFAR-100overall accuracy: 61.54 -> 88.28Improved
add label disambiguation (PhantomGate pseudo targets) to NoiSNCL (ablation)NcPU · CIFAR-100overall accuracy: 50.27 -> 88.28Improved
use noisy-pair robust NoiSNCL instead of supervised non-contrastive L_r (ablation)NcPU · CIFAR-100overall accuracy: 84.58 -> 88.28Improved
use supervised pseudo-label NoiSNCL instead of self-supervised L_self-r (ablation)NcPU · CIFAR-100overall accuracy: 73.22 -> 88.28Improved
use PhantomGate (regret-based update with SAT) instead of plain prototype target s' (ablation)NcPU · CIFAR-100overall accuracy: 75.14 -> 88.28Improved
add SAT negative supervision without regret-based update to prototype disambiguation (ablation)NcPU · CIFAR-100overall accuracy: 75.14 -> 50.25Hurt
add NoiSNCL to uPU (ablation)uPU · CIFAR-100 (real class prior)overall accuracy: 61.68 -> 83.71Improved
add NoiSNCL to nnPU (ablation)nnPU · CIFAR-100 (real class prior)overall accuracy: 71.22 -> 87.81Improved
add NoiSNCL to uPU (ablation)uPU · CIFAR-10 (real class prior)overall accuracy: 69.43 -> 97.35Improved
use NoiSNCL instead of L_r in fully supervised learning (ablation)Supervised · CIFAR-100overall accuracy: 94.45 -> 94.56No clear effect
use NcPU instead of best baseline without auxiliary negativesNcPU · CIFAR-100overall accuracy: 12.89% OA improvementImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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