SOTAVerified

Link Prediction

Link Prediction is a task in graph and network analysis where the goal is to predict missing or future connections between nodes in a network. Given a partially observed network, the goal of link prediction is to infer which links are most likely to be added or missing based on the observed connections and the structure of the network.

( Image credit: Inductive Representation Learning on Large Graphs )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 1949 papers

TitleStatusHype
Topic Modeling and Link-Prediction for Material Property Discovery—0
Graph Collaborative Attention Network for Link Prediction in Knowledge GraphsCode0
Understanding Generalization in Node and Link Prediction—0
Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing—0
Demystifying Distributed Training of Graph Neural Networks for Link PredictionCode0
Directed Link Prediction using GNN with Local and Global Feature Fusion—0
Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networks—0
A Transfer Learning Framework for Multilayer Networks via Model Averaging—0
How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?—0
Learnable Spatial-Temporal Positional Encoding for Link PredictionCode0
Show:102550
← PrevPage 1 of 195Next →
All datasetsFB15k-237WN18RRWN18FB15kYAGO3-10ICEWS05-15ICEWS14CiteseerCoraPubmedWikidata5MGDELT

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AUC200—Unverified
2WalkpoolingAUC98.7—Unverified
3NBFNetAUC98.3—Unverified
4VGNAEAUC97.6—Unverified
5GNAEAUC97.5—Unverified
6Variational graph auto-encodersACC97.1—Unverified
7ARGEAUC96.8—Unverified
8NESSAUC96.67—Unverified
9S-VGAEAUC96—Unverified
10sGraphite-VAEAUC94.8—Unverified