AI Paper Atlas

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

Partial Multi-Label Learning via Large Margin Nearest Neighbour Embeddings

Xiuwen Gong, Dong Yuan, Wei Bao

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 16 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 PML-LMNNE instead of MUSERPML on YeastBP · YeastBPhamming loss: .161±.014 vs .158±.012No clear effect
Use PML-LMNNE instead of PAR-VLSPML on YeastBP · YeastBPaverage precision: .082±.031 -> .152±.023Improved
Use PML-LMNNE instead of MUSERPML on Music-emotion · Music-emotionhamming loss: .284±.023 -> .281±.010No clear effect
Use PML-LMNNE instead of PML-LRSPML on Music-emotion · Music-emotionaverage precision: .516±.014 -> .611±.017Improved
Use PML-LMNNE instead of MUSERPML on Music-style · Music-stylehamming loss: .173±.016 -> .162±.011Improved
Use PML-LMNNE instead of PML-lcPML on Music-style · Music-styleaverage precision: .627±.010 -> .726±.024Improved
Use PML-LMNNE instead of PAR-VLSPML on MIRFlickr · MIRFlickrhamming loss: .193±.017 -> .145±.016Improved
Use PML-LMNNE instead of PAR-VLSPML on MIRFlickr · MIRFlickraverage precision: .685±.017 -> .831±.012Improved
Use PML-LMNNE instead of DRAMAPML on Enron with candidate labels 7 · Enron, candidate labels 7hamming loss: .183±.022 -> .097±.012Improved
Use PML-LMNNE instead of DRAMAPML on Enron with candidate labels 7 · Enron, candidate labels 7average precision: .613±.002 -> .779±.010Improved
Use PML-LMNNE instead of DRAMAPML on CAL500 with candidate labels 45 · CAL500, candidate labels 45hamming loss: .235±.017 -> .260±.013Hurt
Use PML-LMNNE instead of PAR-VLSPML on CAL500 with candidate labels 45 · CAL500, candidate labels 45average precision: .446±.024 -> .615±.021Improved

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