Research map / Graph learning / Graph self-supervised learning
Graph Game Embedding
Xiaobin Hong, Tong Zhang, Zhen Cui, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jian Yang
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 |
|---|---|---|---|
| Use U-PGE instead of DGI | unsupervised node embeddings · Cora | accuracy: 76.9 -> 80.1 | Improved |
| Use U-PGE instead of DGI | unsupervised node embeddings · Citeseer | accuracy: 62.9 -> 63.8 | Improved |
| Use U-PGE instead of DGI | unsupervised node embeddings · Pubmed | accuracy: 73.6 -> 75.4 | Improved |
| Use U-PGE rather than U-GGE | unsupervised node embeddings · Cora | accuracy: 79.6 -> 80.1 | Improved |
| Use U-PGE rather than U-GGE | unsupervised node embeddings · Citeseer | accuracy: 62.7 -> 63.8 | Improved |
| Use U-GGE rather than U-PGE | unsupervised node embeddings · Pubmed | accuracy: 75.4 -> 76.1 | Improved |
| Use S-GGE rather than S-PGE | semi-supervised node embeddings · Cora | accuracy: 83.6 -> 84.0 | Improved |
| Use S-GGE rather than S-PGE | semi-supervised node embeddings · Citeseer | accuracy: 71.9 -> 72.7 | Improved |
| Use S-GGE rather than S-PGE | semi-supervised node embeddings · Pubmed | accuracy: 79.3 -> 80.0 | Improved |
| Use PGE instead of CAN | link prediction · Cora | AUC: 93.4 -> 97.2 | Improved |
| Use PGE instead of CAN | link prediction · Citeseer | AUC: 93.2 -> 98.6 | Improved |
| Use PGE instead of CAN | link prediction · Pubmed | AUC: 96.2 -> 97.7 | Improved |
Closest papers by meaning
- Watch Your Step: Learning Node Embeddings via Graph Attention (NeurIPS 2018 · similarity 0.86)
- Skill Rating for Multiplayer Games. Introducing Hypernode Graphs and their Spectral Theory (JMLR 2020 · similarity 0.86)
- Learning Latent Structures in Network Games via Data-Dependent Gated-Prior Graph Variational Autoencoders (ICML 2024 · similarity 0.85)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.85)
- Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach (ICLR 2024 · similarity 0.85)
- Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning (ICLR 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.
