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 726–750 of 1949 papers

TitleStatusHype
HTGN-BTW: Heterogeneous Temporal Graph Network with Bi-Time-Window Training Strategy for Temporal Link Prediction—0
HUGE: Huge Unsupervised Graph Embeddings with TPUs—0
HyConvE: A Novel Embedding Model for Knowledge Hypergraph Link Prediction with Convolutional Neural Networks—0
HyperQuery: Beyond Binary Link Prediction—0
Graph Anomaly Detection with Graph Neural Networks: Current Status and Challenges—0
Consistencies and inconsistencies between model selection and link prediction in networks—0
Graph Attention Inference of Network Topology in Multi-Agent Systems—0
Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey—0
Cross-Domain Recommendation via Preference Propagation GraphNet—0
How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?—0
Graph-based Generalization Bounds for Learning Binary Relations—0
Graph Based Link Prediction between Human Phenotypes and Genes—0
Class-Balanced and Reinforced Active Learning on Graphs—0
Graph Clustering with Graph Neural Networks—0
Attributed Network Embedding for Learning in a Dynamic Environment—0
Cross view link prediction by learning noise-resilient representation consensus—0
Graph Collaborative Reasoning—0
Forward Backward Similarity Search in Knowledge Networks—0
ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding—0
A Survey on Knowledge Graph Structure and Knowledge Graph Embeddings—0
FOBE and HOBE: First- and High-Order Bipartite Embeddings—0
Adaptive Convolution for Multi-Relational Learning—0
Graph Distance Neural Networks for Predicting Multiple Drug Interactions—0
How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction—0
FMGNN: Fused Manifold Graph Neural Network—0
Show:102550
← PrevPage 30 of 78Next →
All datasetsFB15k-237WN18RRWN18FB15kYAGO3-10ICEWS05-15ICEWS14CiteseerCoraPubmedWikidata5MGDELT

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AutoKGEHits@100.56—Unverified
2CP-N3-RPHits@100.55—Unverified
3DistMult (after variational EM)Hits@100.55—Unverified
4KG-R3Hits@100.54—Unverified
5LASSHits@100.53—Unverified
6MDE_advHits@100.53—Unverified
7GFA-NNHits@100.52—Unverified
8KGRefinerHits@100.49—Unverified
9ComplEx NSCachingHits@100.48—Unverified
10LogicENNHits@100.47—Unverified
#ModelMetricClaimedVerifiedStatus
1MoCoKGCHits@100.88—Unverified
2KERMITHits@100.83—Unverified
3MoCoSAHits@100.82—Unverified
4SimKGCIB(+PB+SN)Hits@100.82—Unverified
5C-LMKE(bert-base)Hits@100.79—Unverified
6LASSHits@100.79—Unverified
7LP-BERTHits@100.75—Unverified
8KGLMHits@100.74—Unverified
9StAR(Self-Adp)Hits@100.71—Unverified
10PALTHits@100.69—Unverified
#ModelMetricClaimedVerifiedStatus
1OpenKE (han2018openke)training time (s)11—Unverified
2LibKGE (ruffinelli2020you)training time (s)10—Unverified
3GraphVite (zhu2019graphvite)training time (s)6—Unverified
4Inverse ModelHits@100.96—Unverified
5QuatDEHits@100.96—Unverified
6LineaREHits@100.96—Unverified
7AutoKGEHits@100.96—Unverified
8MEI (small)Hits@100.96—Unverified
9ComplEx-N3 (reciprocal)Hits@100.96—Unverified
10RotatEHits@100.96—Unverified
#ModelMetricClaimedVerifiedStatus
1OPTransEHits@100.9—Unverified
2AutoKGEMRR0.86—Unverified
3ComplEx-N3 (reciprocal)MRR0.86—Unverified
4LineaREMRR0.84—Unverified
5DistMult (after variational EM)MRR0.84—Unverified
6QuatEMRR0.83—Unverified
7SEEKMRR0.83—Unverified
8MEI-BTDMRR0.81—Unverified
9MEI (small)MRR0.8—Unverified
10pRotatEMRR0.8—Unverified