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 841–850 of 982 papers

TitleStatusHype
Dynamic Graph Representation Learning with Fourier Temporal State EmbeddingCode0
Recursive Neighborhood Pooling for Graph Representation Learning—0
Learning Latent Topology for Graph Matching—0
Beyond COVID-19 Diagnosis: Prognosis with Hierarchical Graph Representation Learning—0
LINGUINE: LearnIng to pruNe on subGraph convolUtIon NEtworks—0
Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs—0
Towards Powerful Graph Neural Networks: Diversity Matters—0
Deep Graph Generators: A Survey—0
Deep Multi-attribute Graph Representation Learning on Protein Structures—0
Hop-Hop Relation-aware Graph Neural Networks—0
Show:102550
← PrevPage 85 of 99Next →

Benchmark Results

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