Research map / Graph learning / Graph self-supervised learning
Graph Agreement Models for Semi-Supervised Learning
Otilia Stretcu, Krishnamurthy Viswanathan, Dana Movshovitz-Attias, Emmanouil Platanios, Sujith Ravi, Andrew Tomkins
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 |
|---|---|---|---|
| add GAM regularization | MLP128 · Cora | accuracy (%): 51.7 -> 80.7 | Improved |
| add GAM regularization | GCN128 · Cora | accuracy (%): 80.9 -> 86.2 | Improved |
| add GAM regularization | GCN128 · Pubmed | accuracy (%): 76.9 -> 86.0 | Improved |
| replace NGM fixed edge weights with learned agreement (GAM) | MLP128 · Cora | accuracy (%): 77.7 -> 80.7 | Improved |
| replace NGM with GAM | GCN1024 · Pubmed | accuracy (%): 68.9 -> 81.6 | Improved |
| add GAM*, no graph | MLP128 · Cora | accuracy (%): 51.7 -> 70.7 | Improved |
| add VATENT | MLP128 · Cora | accuracy (%): 51.7 -> 24.1 | Hurt |
| add GAM* on CNN | CNN · SVHN | accuracy (%): 72.33 -> 83.43 | Improved |
| add GAM* on top of VAT | CNN + VAT · CIFAR-10 | accuracy (%): 64.37 -> 69.64 | Improved |
| add GAM* on top of VATENT | CNN + VATENT · CIFAR-10 | accuracy (%): 66.73 -> 67.29 | Mixed |
| use perfect agreement model instead of learned one (ablation) | MLP128 + GAM · Cora | accuracy (%): 80.7 -> 90.5 | Improved |
| add NGM under noisy graph (<=60% correct edges) (ablation) | MLP128 · Citeseer | accuracy (%) | Hurt |
Closest papers by meaning
- A Flexible Generative Framework for Graph-based Semi-supervised Learning (NeurIPS 2019 · similarity 0.88)
- Label Efficient Semi-Supervised Learning via Graph Filtering (CVPR 2019 · similarity 0.88)
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (ICML 2024 · similarity 0.86)
- Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification (AAAI 2024 · similarity 0.86)
- Label-free Node Classification on Graphs with Large Language Models (LLMs) (ICLR 2024 · similarity 0.86)
- HGDL: Heterogeneous Graph Label Distribution Learning (NeurIPS 2024 · similarity 0.86)
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.
