Generalization Bounds for Graph Embedding Using Negative Sampling: Linear vs Hyperbolic.
Atsushi SuzukiAtsushi NitandaJing WangLinchuan XuKenji YamanishiMarc CavazzaPublished in: NeurIPS (2021)
Keyphrases
- graph embedding
- generalization bounds
- data dependent
- learning theory
- generalization ability
- vc dimension
- model selection
- semi supervised
- discriminant analysis
- dimensionality reduction
- data representation
- low dimensional
- learning problems
- ranking algorithm
- linear classifiers
- sample size
- kernel machines
- distance measure
- pairwise