Link Property Prediction on ogbl-citation2

23개 결과 · ⬇ CSV · JSON

Rank	Model	Ext. data	Test MRR	Validation MRR	Number of params	Paper	Code	Year
1	GraphGPT(d1n30)	No	0.9305 ± 0.0020	0.9295 ± 0.0022	133096832	GraphGPT: Graph Learning with Generative Pre-trained Transformers	alibaba/graph-gpt	2023
2	MPLP	No	0.9072 ± 0.0012	0.9074 ± 0.0011	749757283	Pure Message Passing Can Estimate Common Neighbor for Link Prediction	Barcavin/efficient-node-labelling	2023
3	GraphGPT(SMTP)	No	0.9055 ± 0.0016	0.9042 ± 0.0014	46784128	GraphGPT: Graph Learning with Generative Pre-trained Transformers	alibaba/graph-gpt	2023
4	CFG	No	0.8997 ± 0.0015	0.8987 ± 0.0011	686253	Circle Feature Graphormer: Can Circle Features Stimulate Graph Transformer?	jingsonglv/CFG	2023
5	SIEG	No	0.8957 ± 0.0010	0.8948 ± 0.0008	256802
6	GCN + Heuristic Encoding	No	0.8891 ± 0.0005	0.8892 ± 0.0005	372674	Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods	astroming/GNNHE	2024
7	NGNN + SEAL	No	0.8891 ± 0.0022	0.8879 ± 0.0022	1134402	Network In Graph Neural Network		2021
8	SUREL	No	0.8883 ± 0.0018	0.8891 ± 0.0021	79617	Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning	graph-com/surel · Graph-COM/SUREL · veritasyin/subg_acc	2022
9	S3GRL (PoS Plus)	No	0.8814 ± 0.0008	0.8809 ± 0.0074	142275001	Simplifying Subgraph Representation Learning for Scalable Link Prediction	venomouscyanide/s3grl · venomouscyanide/s3grl_ogb · venomouscyanide/S3GRL_OGB	2023
10	BUDDY	No	0.8796 ± 0.0008	0.8793 ± 0.0008	166531
11	SEAL	No	0.8767 ± 0.0032	0.8757 ± 0.0031	260802	Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning	dmlc/dgl · facebookresearch/SEAL_OGB	2020
12	AGDN w/GraphSAINT	No	0.8549 ± 0.0029	0.8556 ± 0.0033	306716	Adaptive Graph Diffusion Networks	skepsun/SAGN_with_SLE	2020
13	PLNLP	No	0.8492 ± 0.0029	0.8490 ± 0.0031	146514551	Pairwise Learning for Neural Link Prediction	zhitao-wang/PLNLP · zhitao-wang/plnlp	2021
14	Full-batch GCN	No	0.8474 ± 0.0021	0.8479 ± 0.0023	296449	Semi-Supervised Classification with Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · tkipf/gcn · +52	2016
15	HPE - Pre-trained Initialized	No	0.8432 ± 0.0003	0.8422 ± 0.0002	749558528
16	Full-batch GraphSAGE	No	0.8260 ± 0.0036	0.8263 ± 0.0033	460289	Inductive Representation Learning on Large Graphs	pyg-team/pytorch_geometric · dmlc/dgl · dmlc/dgl · +17	2017
17	NeighborSampling (SAGE aggr)	No	0.8044 ± 0.0010	0.8054 ± 0.0009	460289	Inductive Representation Learning on Large Graphs	pyg-team/pytorch_geometric · dmlc/dgl · dmlc/dgl · +17	2017
18	ClusterGCN (GCN aggr)	No	0.8004 ± 0.0025	0.7994 ± 0.0025	296449	Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks	google-research/google-research · dmlc/dgl · benedekrozemberczki/ClusterGCN · +3	2019
19	GraphSAINT (GCN aggr)	No	0.7985 ± 0.0040	0.7975 ± 0.0039	296449	GraphSAINT: Graph Sampling Based Inductive Learning Method	dmlc/dgl · GraphSAINT/GraphSAINT · thudm/graphmae2 · +5	2019
20	Node2vec	No	0.6141 ± 0.0011	0.6124 ± 0.0011	374911105	node2vec: Scalable Feature Learning for Networks	dmlc/dgl · shenweichen/GraphEmbedding · aditya-grover/node2vec · +17	2016