AI Paper Atlas

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

Learning from Label Proportions via Proportional Value Classification

Tianhao Ma, Wei Wang, Ximing Li, Gang Niu, Masashi Sugiyama

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning

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
replace proportion matching (PM) with proportional value classificationPM · K-MNIST (Random Bag, bag size 128)accuracy: 28.30 -> 96.36Improved
replace PM with LLP-PVCPM · CIFAR-10 (Random Bag, bag size 128)accuracy: 49.21 -> 76.01Improved
replace ROT with LLP-PVCROT · CIFAR-10 (Random Bag, bag size 128)accuracy: 33.70 -> 76.01Improved
replace ROT with LLP-PVCROT · SVHN (Cluster Bag, bag size 128)accuracy: 58.33 -> 93.89Improved
replace ROT with LLP-PVCROT · K-MNIST (alpha-First Bag, bag size 128)accuracy: 54.59 -> 96.03Improved
replace ROT with LLP-PVC at small bagsROT · F-MNIST (Random Bag, bag size 4)accuracy: 91.43 -> 91.39No clear effect
increase bag size from 4 to 128 for LLP-PVCLLP-PVC · K-MNIST (Random Bag)accuracy: 96.55 -> 96.36No clear effect
increase bag size from 4 to 128 for LLP-PVCLLP-PVC · CIFAR-10 (Random Bag)accuracy: 84.34 -> 76.01Hurt
add flooding regularization to EasyLLPEasyLLP · CIFAR-10 (Random Bag, bag size 128)accuracy: 37.36 -> 47.54Improved
add flooding regularization to EasyLLPEasyLLP · K-MNIST (Cluster Bag, bag size 4)accuracy: 31.61 -> 60.95Improved
use FFT divide-and-conquer instead of dynamic programming for the loss (ablation)LLP-PVC (DP) · runtime vs bag sizeexecution timeImproved
use LLP-PVC instead of Count LossCount Loss · CIFAR-10 (bag size 8)execution time: 139.52 -> 3.01Improved

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