SOTAVerified

Graph Representation Learning

The goal of Graph Representation Learning is to construct a set of features (‘embeddings’) representing the structure of the graph and the data thereon. We can distinguish among Node-wise embeddings, representing each node of the graph, Edge-wise embeddings, representing each edge in the graph, and Graph-wise embeddings representing the graph as a whole.

Source: SIGN: Scalable Inception Graph Neural Networks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 621–630 of 982 papers

TitleStatusHype
Classic Graph Structural Features Outperform Factorization-Based Graph Embedding Methods on Community LabelingCode0
Identifying critical nodes in complex networks by graph representation learning—0
Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagationCode1
Dual Space Graph Contrastive Learning—0
Learning Hierarchical Graph Representation for Image Manipulation Detection—0
GraphVAMPNet, using graph neural networks and variational approach to markov processes for dynamical modeling of biomolecules—0
Local2Global: A distributed approach for scaling representation learning on graphsCode0
Graph Representation Learning for Multi-Task Settings: a Meta-Learning ApproachCode1
FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph EditingCode0
Spatio-Temporal Graph Representation Learning for Fraudster Group Detection—0
Show:102550
← PrevPage 63 of 99Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pi-net-linearError (mm)0.47—Unverified