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 661–670 of 982 papers

TitleStatusHype
Learning node embeddings via summary graphs: a brief theoretical analysis—0
MM-GATBT: Enriching Multimodal Representation Using Graph Attention NetworkCode0
Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning—0
Causal Machine Learning: A Survey and Open Problems—0
Dynamic Community Detection via Adversarial Temporal Graph Representation Learning—0
Iso-CapsNet: Isomorphic Capsule Network for Brain Graph Representation LearningCode0
MultiSAGE: a multiplex embedding algorithm for inter-layer link prediction—0
Transferable Graph Backdoor Attack—0
Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation LearningCode0
NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation LearningCode0
Show:102550
← PrevPage 67 of 99Next →

Benchmark Results

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