Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space.
Josephine Maria ThomasAlessandro MuscoloniSara CiucciGinestra BianconiCarlo Vittorio CannistraciPublished in: CoRR (2016)
Keyphrases
- machine learning
- dimensionality reduction
- network structure
- low dimensional
- network topologies
- embedding space
- complex networks
- multi dimensional scaling
- fully connected
- network design
- network model
- network size
- heterogeneous networks
- computer networks
- artificial intelligence
- community structure
- network parameters
- scale free
- cellular networks
- pattern recognition
- peer to peer
- network resources
- social networks
- counter propagation
- graph embedding
- high dimensional
- recurrent networks
- computer science
- input space
- low dimensional spaces
- lower dimensional
- power law
- support vector machine
- nonlinear dimensionality reduction
- vector space
- peer to peer overlay
- telecommunication networks
- latent space
- learning algorithm
- feature extraction
- network traffic
- communication networks
- space requirements
- multidimensional scaling
- real world networks
- mobile nodes
- network analysis
- euclidean space
- manifold learning
- centrality measures
- locality preserving projections
- structure preserving
- high dimensional data
- face recognition
- access points