AI Paper Atlas

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

Enhancing Conformal Prediction via Class Similarity

Ariel Fargion, Lahav Dabah, Tom Tirer

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled 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 model-agnostic out-of-group penalty (MA-CS)RAPS · CIFAR-100 ResNet34, alpha=0.05average set size: 5.79 -> 4.52Improved
add model-specific similarity penalty (MS-CS)RAPS · CIFAR-100 ResNet34, alpha=0.05average set size: 5.79 -> 3.79Improved
add model-agnostic penalty (MA-CS)RAPS · CIFAR-100 ResNet34, alpha=0.05#superclasses in set: 3.40 -> 2.29Improved
add model-specific penalty (MS-CS)LAC · CIFAR-100 ResNet50, alpha=0.05average set size: 3.68 -> 2.92Improved
add model-specific penalty (MS-CS)SAPS · CIFAR-100 ResNet50, alpha=0.05average set size: 3.45 -> 3.14Improved
use MS-CS instead of MA-CSCP with class-similarity penalty · CIFAR-100 ResNet34, RAPS, alpha=0.05average set size: 4.52 -> 3.79Improved
replace score-based class clustering (Clustered CP) vs standardLAC/RAPS/SAPS · CIFAR-100 ResNet50, alpha=0.1average set size: 1.62 -> 1.82 (LAC)Hurt
use hierarchical AIR baseline instead of standard scoreRAPS · CIFAR-100 ResNet34, alpha=0.05average set size: 5.79 -> 15.15Hurt
use AIR instead of standard scoreRAPS · CIFAR-100 ResNet34, alpha=0.05#superclasses in set: 3.40 -> 3.03Improved
increase penalty lambda from zero to small values (ablation)RAPS + MA-CS · CIFAR-100 ResNet50, alpha=0.1average set sizeImproved
increase penalty lambda to large values (ablation)RAPS + MA-CS · CIFAR-100 ResNet50, alpha=0.1average set sizeHurt
vary lambda (ablation)RAPS + MA-CS · CIFAR-100 ResNet50, alpha=0.1worst class-conditional coverage gapNo 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