GeneralizationErrorBoundsforGraphEmbedding UsingNegativeSampling: LinearvsHyperbolic
–Neural Information Processing Systems
Inthis paper,we provide ageneralization error bound applicable for graph embedding both in linear and hyperbolic spaces under various negative sampling settings that appear in graph embedding.
Neural Information Processing Systems
Feb-18-2026, 21:55:07 GMT
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America > United States
- Nevada (0.04)
- Louisiana (0.04)
- New York
- Richmond County > New York City (0.04)
- Queens County > New York City (0.04)
- New York County > New York City (0.04)
- Kings County > New York City (0.04)
- Bronx County > New York City (0.04)
- Georgia > Fulton County
- Atlanta (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- Europe > Italy
- Asia
- China (0.04)
- Japan
- Kyūshū & Okinawa > Kyūshū
- Fukuoka Prefecture > Fukuoka (0.04)
- Honshū > Kantō
- Tokyo Metropolis Prefecture > Tokyo (0.15)
- Kyūshū & Okinawa > Kyūshū
- Oceania > Australia
- Technology: