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 51–60 of 982 papers

TitleStatusHype
Bi-GCN: Binary Graph Convolutional NetworkCode1
A Meta-Learning Approach for Graph Representation Learning in Multi-Task SettingsCode1
Does Graph Distillation See Like Vision Dataset Counterpart?Code1
Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily DiscriminatingCode1
A critical look at the evaluation of GNNs under heterophily: Are we really making progress?Code1
An adaptive graph learning method for automated molecular interactions and properties predictionsCode1
Adversarial Graph DisentanglementCode1
Dynamic Graph Learning Based on Hierarchical Memory for Origin-Destination Demand PredictionCode1
Large-Scale Representation Learning on Graphs via BootstrappingCode1
A step towards neural genome assemblyCode1
Show:102550
← PrevPage 6 of 99Next →

Benchmark Results

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