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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1801–1810 of 1949 papers

Title	Date	Tasks	Status
On Generalization of Graph Autoencoders with Adversarial Training	Jul 6, 2021	Anomaly DetectionClustering	CodeCode Available
On the Equivalence between Positional Node Embeddings and Structural Graph Representations	Oct 1, 2019	Inductive LearningLink Prediction	CodeCode Available
On the Initialization of Graph Neural Networks	Dec 5, 2023	Graph ClassificationGraph Representation Learning	CodeCode Available
On the Use of ArXiv as a Dataset	Apr 30, 2019	ArticlesAuthor Attribution	CodeCode Available
OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs	May 30, 2022	Link Prediction	CodeCode Available
OpenBioLink: A benchmarking framework for large-scale biomedical link prediction	Dec 10, 2019	BenchmarkingBIG-bench Machine Learning	CodeCode Available
Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs	Nov 1, 2021	Link PredictionPrediction	CodeCode Available
Open-World Knowledge Graph Completion	Nov 9, 2017	Entity LinkingKnowledge Graph Completion	CodeCode Available
Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Prediction	Apr 4, 2025	Graph EmbeddingKnowledge Graph Embedding	CodeCode Available
Out-of-Vocabulary Entities in Link Prediction	May 26, 2021	Graph EmbeddingKnowledge Graph Embedding	CodeCode Available

Show:10 25 50

← PrevPage 181 of 195Next →

All datasets FB15k-237 WN18RR WN18 FB15k YAGO3-10 ICEWS05-15 ICEWS14 Citeseer Cora Pubmed Wikidata5M GDELT

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	AutoKGE	Hits@10	0.56	—	Unverified
2	CP-N3-RP	Hits@10	0.55	—	Unverified
3	DistMult (after variational EM)	Hits@10	0.55	—	Unverified
4	KG-R3	Hits@10	0.54	—	Unverified
5	LASS	Hits@10	0.53	—	Unverified
6	MDE_adv	Hits@10	0.53	—	Unverified
7	GFA-NN	Hits@10	0.52	—	Unverified
8	KGRefiner	Hits@10	0.49	—	Unverified
9	ComplEx NSCaching	Hits@10	0.48	—	Unverified
10	LogicENN	Hits@10	0.47	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MoCoKGC	Hits@10	0.88	—	Unverified
2	KERMIT	Hits@10	0.83	—	Unverified
3	MoCoSA	Hits@10	0.82	—	Unverified
4	SimKGCIB(+PB+SN)	Hits@10	0.82	—	Unverified
5	C-LMKE(bert-base)	Hits@10	0.79	—	Unverified
6	LASS	Hits@10	0.79	—	Unverified
7	LP-BERT	Hits@10	0.75	—	Unverified
8	KGLM	Hits@10	0.74	—	Unverified
9	StAR(Self-Adp)	Hits@10	0.71	—	Unverified
10	PALT	Hits@10	0.69	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	OpenKE (han2018openke)	training time (s)	11	—	Unverified
2	LibKGE (ruffinelli2020you)	training time (s)	10	—	Unverified
3	GraphVite (zhu2019graphvite)	training time (s)	6	—	Unverified
4	Inverse Model	Hits@10	0.96	—	Unverified
5	QuatDE	Hits@10	0.96	—	Unverified
6	LineaRE	Hits@10	0.96	—	Unverified
7	AutoKGE	Hits@10	0.96	—	Unverified
8	MEI (small)	Hits@10	0.96	—	Unverified
9	ComplEx-N3 (reciprocal)	Hits@10	0.96	—	Unverified
10	RotatE	Hits@10	0.96	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	OPTransE	Hits@10	0.9	—	Unverified
2	AutoKGE	MRR	0.86	—	Unverified
3	ComplEx-N3 (reciprocal)	MRR	0.86	—	Unverified
4	LineaRE	MRR	0.84	—	Unverified
5	DistMult (after variational EM)	MRR	0.84	—	Unverified
6	QuatE	MRR	0.83	—	Unverified
7	SEEK	MRR	0.83	—	Unverified
8	MEI-BTD	MRR	0.81	—	Unverified
9	MEI (small)	MRR	0.8	—	Unverified
10	pRotatE	MRR	0.8	—	Unverified