Research map / Graph learning / Graph self-supervised learning
Co-GCN for Multi-View Semi-Supervised Learning
Shu Li, Wen-Tao Li, Wei Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| learn adaptive per-view Laplacian weights instead of shared max-combined graph (ablation) | GCN with Ac · HW (10% labeled) | accuracy: 89.69 -> 97.65 | Improved |
| learn adaptive Laplacian weights instead of shared max-combined graph (ablation) | GCN with Ac · Citeseer (1% labeled) | accuracy: 62.94 -> 61.91 | Hurt |
| learn adaptive Laplacian weights instead of shared max-combined graph (ablation) | GCN with Ac · Cora (10% labeled) | accuracy: 82.41 -> 82.59 | No clear effect |
| use cross-view graph information instead of per-view GCN fusion (ablation) | GCN fusion · Cora (1% labeled) | accuracy: 67.56 -> 73.11 | Improved |
| Co-GCN vs multi-view baselines at 1% labels | multi-view SSL · HW, Cal20 (1% labeled) | accuracy: 95.02 vs 92.00 (HW, MLAN) | Hurt |
| Co-GCN vs multi-view baselines at 10% labels | multi-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 datasets | accuracy | Improved |
Closest papers by meaning
- Semi-Supervised Learning With Graph Learning-Convolutional Networks (CVPR 2019 · similarity 0.89)
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning (AAAI 2018 · similarity 0.89)
- GMV: A Unified and Efficient Graph Multi-View Learning Framework (NeurIPS 2025 · similarity 0.87)
- Multi-view adaptive graph convolutions for graph classification (ECCV 2020 · similarity 0.87)
- View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (CVPR 2020 · similarity 0.87)
- Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view Clustering (AAAI 2025 · similarity 0.85)
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.
