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:
- North America
- United States (0.14)
- Canada > Quebec
- Capitale-Nationale Region
- Québec (0.04)
- Quebec City (0.04)
- Capitale-Nationale Region
- Asia
- Middle East > Jordan (0.04)
- China
- Guangdong Province > Shenzhen (0.04)
- Hong Kong (0.04)
- North America
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Health & Medicine (0.45)
- Technology: