SOTAVerified

Network Embedding

Network Embedding, also known as "Network Representation Learning", is a collective term for techniques for mapping graph nodes to vectors of real numbers in a multidimensional space. To be useful, a good embedding should preserve the structure of the graph. The vectors can then be used as input to various network and graph analysis tasks, such as link prediction

Source: Tutorial on NLP-Inspired Network Embedding

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 403 papers

TitleStatusHype
Global Vectors for Node RepresentationsCode0
Gradient-Based Spectral Embeddings of Random Dot Product GraphsCode0
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask DependenciesCode0
JNET: Learning User Representations via Joint Network Embedding and Topic EmbeddingCode0
Attributed Network Embedding for Incomplete Attributed NetworksCode0
A Hybrid Membership Latent Distance Model for Unsigned and Signed Integer Weighted NetworksCode0
Font Size: Community Preserving Network EmbeddingCode0
Flexible Attributed Network EmbeddingCode0
Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information NetworksCode0
Adversarial Attack on Network Embeddings via Supervised Network PoisoningCode0
Show:102550
← PrevPage 8 of 41Next →

No leaderboard results yet.