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 411–420 of 982 papers

TitleStatusHype
A Dataset for Learning Graph Representations to Predict Customer Returns in Fashion Retail—0
FTM: A Frame-level Timeline Modeling Method for Temporal Graph Representation LearningCode1
Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks—0
Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations—0
A critical look at the evaluation of GNNs under heterophily: Are we really making progress?Code1
A General-Purpose Transferable Predictor for Neural Architecture Search—0
Learnable Topological Features for Phylogenetic Inference via Graph Neural NetworksCode1
Creating generalizable downstream graph models with random projections—0
Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection—0
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural NetworksCode1
Show:102550
← PrevPage 42 of 99Next →

Benchmark Results

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