AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Co-GCN for Multi-View Semi-Supervised Learning

Shu Li, Wen-Tao Li, Wei Wang

AAAI 2020 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 107 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
learn adaptive per-view Laplacian weights instead of shared max-combined graph (ablation)GCN with Ac · HW (10% labeled)accuracy: 89.69 -> 97.65Improved
learn adaptive Laplacian weights instead of shared max-combined graph (ablation)GCN with Ac · Citeseer (1% labeled)accuracy: 62.94 -> 61.91Hurt
learn adaptive Laplacian weights instead of shared max-combined graph (ablation)GCN with Ac · Cora (10% labeled)accuracy: 82.41 -> 82.59No clear effect
use cross-view graph information instead of per-view GCN fusion (ablation)GCN fusion · Cora (1% labeled)accuracy: 67.56 -> 73.11Improved
Co-GCN vs multi-view baselines at 1% labelsmulti-view SSL · HW, Cal20 (1% labeled)accuracy: 95.02 vs 92.00 (HW, MLAN)Hurt
Co-GCN vs multi-view baselines at 10% labelsmulti-view SSL · 8 datasets (10% labeled)accuracy: 71.58 -> 82.59 (Cora vs MKL)Improved
use larger k for k-NN graph instead of 1-NN (ablation)Co-GCN · all datasetsaccuracyImproved

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