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 171–180 of 403 papers

TitleStatusHype
Learning to Embed Categorical Features without Embedding Tables for Recommendation—0
TriNE: Network Representation Learning for Tripartite Heterogeneous Networks—0
Inductive Graph Embeddings through Locality Encodings—0
EPNE: Evolutionary Pattern Preserving Network Embedding—0
Sub-graph Contrast for Scalable Self-Supervised Graph Representation LearningCode1
Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation—0
Learning a Deep Part-based Representation by Preserving Data Distribution—0
Layer-stacked Attention for Heterogeneous Network Embedding—0
Boosting House Price Predictions using Geo-Spatial Network EmbeddingCode0
Adversarial Privacy Preserving Graph Embedding against Inference AttackCode1
Show:102550
← PrevPage 18 of 41Next →

No leaderboard results yet.