AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Partial Optimal Tranport with applications on Positive-Unlabeled Learning

Laetitia Chapel, Mokhtar Z. Alaya, Gilles Gasso

NeurIPS 2020 · Learning theory and algorithms › Optimal transport · approach: Transport map estimation · 30 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
use partial-W instead of PU/PUSBPU learning · UCI datasets (SCAR), e.g. USPSaccuracy (%): 95.4 -> 98.3 (USPS); 65.6 -> 55.6 (Connect-4); 84.3 -> 78.0 (Spambase)Mixed
use partial-GW instead of partial-WPU learning · UCI datasets (SCAR)accuracy (%): 96.3 -> 95.0 (Mushrooms); 78.0 -> 70.2 (Spambase)Hurt
add 0.025 noise level assumption for Pos (ablation)partial-W · UCI datasets (SCAR)accuracy (%): 96.3 -> 96.4 (Mushrooms); 55.6 -> 61.7 (Connect-4)No clear effect
use partial-GW instead of partial-W under covariate shiftPU learning · Colored MNIST (SAR)accuracy (%): 91.5 -> 97.3Improved
use partial-GW instead of partial-W across different domainsPU learning · Caltech Office DeCAF c->daccuracy (%): 80.8 -> 94.2Improved
use partial-GW instead of partial-W on same domainPU learning · DeCAF c->caccuracy (%): 94.0 -> 86.4Hurt
use partial-GW instead of PU methods on SURF c->aPU learning · SURF c->aaccuracy (%): 87.7 (PU) vs 85.6 (p-GW)Mixed

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