AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Multi-View Representation Learning with Manifold Smoothness

Shu Li, Wei Wang, Wen-Tao Li, Pan Chen

AAAI 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 7 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
Use MvDGAT with manifold-aware graph attention instead of MDNNsemi-supervised multi-view representation learning · FOXaccuracy: 0.673 -> 0.776Improved
Use MvDGAT with manifold-aware graph attention instead of MDNNsemi-supervised multi-view representation learning · CNNaccuracy: 0.354 -> 0.670Improved
Use MvDGAT with manifold-aware graph attention instead of MDNNsemi-supervised multi-view representation learning · Ads13accuracy: 0.950 -> 0.945Hurt
Use MvDGAT with manifold-aware graph attention instead of MDNNsemi-supervised multi-view representation learning · CoursePurity: 0.815 -> 0.931Improved
Use MvDGAT with manifold-aware graph attention instead of MDNNsemi-supervised multi-view representation learning · FOXPurity: 0.543 -> 0.718Improved
Use MvDGAT with manifold-aware graph attention instead of MDNNsemi-supervised multi-view representation learning · CNNPurity: 0.366 -> 0.484Improved
Use MvDGAT with manifold-aware graph attention instead of MDNNsemi-supervised multi-view representation learning · NoisyMNISTPurity: 0.679 -> 0.893Improved

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