MDGCL: Graph Contrastive Learning Framework with Multiple Graph Diffusion Methods.
Yuqiang LiYi ZhangChun LiuPublished in: Neural Process. Lett. (2024)
Keyphrases
- graph based algorithm
- empirical studies
- spectral embedding
- structured data
- graph theory
- graph theoretical
- learning scheme
- multi view learning
- significant improvement
- graph matching
- multiple tasks
- graph representation
- random walk
- combining multiple
- learning process
- learning frameworks
- graph construction
- learning algorithm
- learning tasks
- directed graph
- connected components
- online learning
- graph mining
- discriminative learning
- latent variable models
- bipartite graph
- supervised learning
- human experts