Graph Classification via Reference Distribution Learning: Theory and Practice
–Neural Information Processing Systems
This work introduces Graph Reference Distribution Learning (GRDL), an efficient and accurate graph classification method. GRDL treats each graph's latent node embeddings given by GNN layers as a
Neural Information Processing Systems
Feb-18-2026, 18:26:24 GMT
- Country:
- Asia
- China
- Guangdong Province > Shenzhen (0.04)
- Hong Kong (0.04)
- Middle East > Jordan (0.04)
- China
- North America
- Canada > Quebec
- Capitale-Nationale Region
- Quebec City (0.04)
- Québec (0.04)
- Capitale-Nationale Region
- United States (0.14)
- Canada > Quebec
- Asia
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Health & Medicine (0.45)
- Technology: