AI Paper Atlas

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

Scalable Generative Models for Multi-label Learning with Missing Labels

Vikas Jain, Nirbhay Modhe, Piyush Rai

ICML 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 21 citations (OpenAlex)

Read the paper

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
turn on label exposure model (ablation)GenEML · Synthetic multi-label dataPrecision@1: 79.2 -> 87.8Improved
turn on label exposure model (ablation)GenEML · Synthetic multi-label dataPrecision@3: 59.0 -> 65.2Improved
turn on label exposure model (ablation)GenEML · Synthetic multi-label dataPrecision@2: 68.9 -> 75.2Improved
model label exposure versus LEML without exposureGenEML · Synthetic multi-label dataPrecision@1: 78.8 -> 87.8Improved
GenEML versus best baselineGenEML · BibtexPrecision@1: 63.46 -> 64.09Improved
GenEML versus best baselineGenEML · MediamillPrecision@1: 84.22 -> 87.15Improved
GenEML versus best baselineGenEML · Eurlex-4KPrecision@1: 76.43 -> 77.75Improved
GenEML versus LEMLGenEML · MovielensPrecision@1: 54.22 -> 55.78Improved
GenEML (online EM) versus LEML on large-scale RCVGenEML · RCV-2KPrecision@1: 89.09 -> 87.21Hurt
GenEML (online EM) versus PfasterXML on Wiki10-31KGenEML · Wiki10-31KPrecision@5: 59.10 -> 32.06Hurt
online EM instead of batch EMGenEML · Bibtex and Mediamillconvergence timeImproved
use first-order gradient updates for W instead of CG on very large dataGenEML online EM · large-scale datamemory and speedImproved

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