Graph Property Prediction on ogbg-code2

21개 결과 · ⬇ CSV · JSON

Test F1 score

Rank	Model	Test F1 score	Ext. data	Validation F1 score	Number of params	Paper	Code	Year
1	SAT++ with Magnetic Laplacian	0.2222 ± 0.0010	No	0.2044 ± 0.0020	14378069	Transformers Meet Directed Graphs	deepmind/digraph_transformer	2023
2	SAT++ with Magnetic Laplacian	0.2222 ± 0.0032	No	0.2044 ± 0.0020	14378069
3	DAGformer	0.2018 ± 0.0021	No	0.1846 ± 0.0010	14952882	Transformers over Directed Acyclic Graphs	LUOyk1999/DAGformer	2022
4	SAT	0.1937 ± 0.0028	No	0.1773 ± 0.0023	15734000	Structure-Aware Transformer for Graph Representation Learning	BorgwardtLab/SAT · borgwardtlab/sat · borgwardtlab/pst	2022
5	GatedGCN+	0.1896 ± 0.0024	–	0.1742 ± 0.0027	–	Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence	LUOyk1999/GNNPlus	2025
6	GPS	0.1894	No	0.1739 ± 0.001	12454066	Recipe for a General, Powerful, Scalable Graph Transformer	rampasek/GraphGPS · hamed1375/exphormer · graphcore/ogb-lsc-pcqm4mv2 · +1	2022
7	GraphTrans (GCN-Virtual)	0.1830 ± 0.0024	No	0.1661 ± 0.0012	9053246
8	GMAN+bag of tricks	0.1770 ± 0.0012	No	0.1631 ± 0.0090	63684290
9	DAGNN	0.1751 ± 0.0049	No	0.1607 ± 0.0040	35246814
10	DAGNN	0.1751 ± 0.0049	–	0.1607 ± 0.0040	–	Directed Acyclic Graph Neural Networks	vthost/DAGNN	2021
11	GraphTrans (GCN)	0.1751 ± 0.0015	No	0.1599 ± 0.0009	7563746
12	EGC-M (No Edge Features)	0.1595 ± 0.0019	No	0.1464 ± 0.0021	10986002	Do We Need Anisotropic Graph Neural Networks?	pyg-team/pytorch_geometric · shyam196/egc	2021
13	GCN+virtual node	0.1595 ± 0.0018	No	0.1461 ± 0.0013	12484310	Semi-Supervised Classification with Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · tkipf/gcn · +52	2016
14	GIN+virtual node	0.1581 ± 0.0026	No	0.1439 ± 0.0020	13841815	How Powerful are Graph Neural Networks?	dmlc/dgl · dmlc/dgl · weihua916/powerful-gnns · +16	2018
15	PNA (No Edge Features)	0.1570 ± 0.0032	No	0.1453 ± 0.0025	10992050	Do We Need Anisotropic Graph Neural Networks?	pyg-team/pytorch_geometric · shyam196/egc	2021
16	GAT	0.1569 ± 0.0010	No	0.1442 ± 0.0017	11030210	Graph Attention Networks	labmlai/annotated_deep_learning_paper_implementations · dmlc/dgl · dmlc/dgl · +90	2017
17	MPNN-Max (No Edge Features)	0.1552 ± 0.0022	No	0.1441 ± 0.0016	10971506	Do We Need Anisotropic Graph Neural Networks?	pyg-team/pytorch_geometric · shyam196/egc	2021
18	EGC-S (No Edge Features)	0.1528 ± 0.0025	No	0.1427 ± 0.0020	11156530	Do We Need Anisotropic Graph Neural Networks?	pyg-team/pytorch_geometric · shyam196/egc	2021
19	GCN	0.1507 ± 0.0018	No	0.1399 ± 0.0017	11033210	Semi-Supervised Classification with Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · tkipf/gcn · +52	2016
20	GIN	0.1495 ± 0.0023	No	0.1376 ± 0.0016	12390715	How Powerful are Graph Neural Networks?	dmlc/dgl · dmlc/dgl · weihua916/powerful-gnns · +16	2018