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 431–440 of 982 papers

TitleStatusHype
Hierarchical and Unsupervised Graph Representation Learning with Loukas's CoarseningCode0
HopfE: Knowledge Graph Representation Learning using Inverse Hopf FibrationsCode0
DINE: Dimensional Interpretability of Node EmbeddingsCode0
Embedding Graphs on Grassmann ManifoldCode0
EGAD: Evolving Graph Representation Learning with Self-Attention and Knowledge Distillation for Live Video Streaming EventsCode0
Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series ClassificationCode0
Het-node2vec: second order random walk sampling for heterogeneous multigraphs embeddingCode0
Robust Graph Representation Learning via Neural SparsificationCode0
HeGAE-AC: heterogeneous graph auto-encoder for attribute completionCode0
Neural Causal Graph Collaborative FilteringCode0
Show:102550
← PrevPage 44 of 99Next →

Benchmark Results

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