Research map / Graph learning / Graph self-supervised learning
Semi-Supervised Classification with Graph Convolutional Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GCN instead of the strongest reported baseline, ICA | Semi-supervised node classification · Citeseer | accuracy: 69.1 -> 70.3 | Helped |
| Use GCN instead of the strongest reported baseline, Planetoid* | Semi-supervised node classification · Cora | accuracy: 75.7 -> 81.5 | Helped |
| Use GCN instead of the strongest reported baseline, Planetoid* | Semi-supervised node classification · Pubmed | accuracy: 77.2 -> 79.0 | Helped |
| Use GCN instead of the strongest reported baseline, Planetoid* | Semi-supervised node classification · NELL | accuracy: 61.9 -> 66.0 | Helped |
| Use the renormalization trick instead of Chebyshev filter K=3 (ablation) | GCN · Citeseer, Cora, Pubmed | accuracy: 69.8 -> 70.3; 79.5 -> 81.5; 74.4 -> 79.0 | Helped |
| Use the renormalization trick instead of Chebyshev filter K=2 (ablation) | GCN · Citeseer, Cora, Pubmed | accuracy: 69.6 -> 70.3; 81.2 -> 81.5; 73.8 -> 79.0 | Helped |
| Use the renormalization trick instead of the first-order model (ablation) | GCN · Citeseer, Cora, Pubmed | accuracy: 68.3 -> 70.3; 80.0 -> 81.5; 77.5 -> 79.0 | Helped |
| Use the renormalization trick instead of single-parameter propagation (ablation) | GCN · Citeseer, Cora, Pubmed | accuracy: 69.3 -> 70.3; 79.2 -> 81.5; 77.4 -> 79.0 | Helped |
| Use the renormalization trick instead of first-order-term-only propagation (ablation) | GCN · Citeseer, Cora, Pubmed | accuracy: 68.7 -> 70.3; 80.5 -> 81.5; 77.8 -> 79.0 | Helped |
| Use graph propagation instead of an MLP (ablation) | GCN · Citeseer, Cora, Pubmed | accuracy: 46.5 -> 70.3; 55.1 -> 81.5; 71.4 -> 79.0 | Helped |
Closest papers by meaning
- Semi-Supervised Learning With Graph Learning-Convolutional Networks (CVPR 2019 · similarity 0.93)
- Learning Convolutional Neural Networks for Graphs (ICML 2016 · similarity 0.92)
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning (AAAI 2018 · similarity 0.92)
- Convolutional Kernel Networks for Graph-Structured Data (ICML 2020 · similarity 0.92)
- Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning (AAAI 2020 · similarity 0.91)
- Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification (AAAI 2024 · similarity 0.90)
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.