AI Paper Atlas

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

Efficient Training for Positive Unlabeled Learning

Emanuele Sansone, Francesco G. B. De Natale, Zhi‐Hua Zhou

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data

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
run USMO optimization after the proposed initialization instead of initialization alone (ablation)USMO · UCI small-scale, linear kernel, lambda=0.0001F-measure: 55.7 -> 67.6Improved
run USMO optimization after the proposed initialization instead of initialization alone (ablation)USMO · UCI small-scale, Gaussian kernel, lambda=0.0001F-measure: 45.7 -> 66.3Improved
run USMO optimization after the proposed initialization instead of initialization alone (ablation)USMO · UCI small-scale, linear kernel, lambda=0.1F-measure: 62.7 -> 74.3Improved
use USMO instead of the quadprog interior-point solver of the same problemUSMO · UCI small-scale, linear kernel, lambda=0.01F-measure: 71.2 -> 71.3No clear effect
use USMO instead of the quadprog interior-point solver of the same problemUSMO · UCI small-scale, Gaussian kernel, lambda=0.001F-measure: 69.2 -> 68.9No clear effect
use USMO instead of the ramp-loss baseline in the first comparison columnUSMO · UCI small-scale, linear kernel, lambda=0.0001F-measure: 65.1 -> 67.6Improved
use USMO instead of the ramp-loss baseline in the first comparison columnUSMO · UCI small-scale, Gaussian kernel, lambda=0.0001F-measure: 62.3 -> 66.3Improved
use USMO instead of the ramp-loss baseline in the first comparison columnUSMO · UCI small-scale, Gaussian kernel, lambda=0.01F-measure: 68.6 -> 68.4No 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