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 701–710 of 982 papers

TitleStatusHype
GraphGT: Machine Learning Datasets for Graph Generation and TransformationCode1
Edge but not Least: Cross-View Graph Pooling—0
AutoGCL: Automated Graph Contrastive Learning via Learnable View GeneratorsCode1
Graphine: A Dataset for Graph-aware Terminology Definition GenerationCode0
X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning—0
Pointspectrum: Equivariance Meets Laplacian Filtering for Graph Representation Learning—0
Graph-based Incident Aggregation for Large-Scale Online Service SystemsCode0
ETA Prediction with Graph Neural Networks in Google Maps—0
Jointly Learnable Data Augmentations for Self-Supervised GNNsCode1
HopfE: Knowledge Graph Representation Learning using Inverse Hopf FibrationsCode0
Show:102550
← PrevPage 71 of 99Next →

Benchmark Results

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