Graph Classification on IMDb-B

102개 결과 · ⬇ CSV · JSON

Accuracy

Rank	Model	Accuracy	Accuracy (10-fold)	Rand index	Extra Training Data	Paper	Code	Year
1	U2GNN (Unsupervised)	96.41%	–	–		Universal Graph Transformer Self-Attention Networks	daiquocnguyen/Graph-Transformer	2019
2	ESA (Edge set attention, no positional encodings)	86.250±0.957	–	–		An end-to-end attention-based approach for learning on graphs	davidbuterez/edge-set-attention	2024
3	GAT	84.250±2.062	–	–		Graph Attention Networks	labmlai/annotated_deep_learning_paper_implementations · dmlc/dgl · dmlc/dgl · +90	2017
4	MEWISPool	82.13%	–	–		Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks	mewispool/mewispool	2021
5	GIN	81.250±3.775	–	–		How Powerful are Graph Neural Networks?	dmlc/dgl · dmlc/dgl · weihua916/powerful-gnns · +16	2018
6	TokenGT	80.250±3.304	–	–		Pure Transformers are Powerful Graph Learners	jw9730/tokengt · luis-mueller/wl-transformers	2022
7	GATv2	80.000±2.739	–	–		How Attentive are Graph Attention Networks?	labmlai/annotated_deep_learning_paper_implementations · rusty1s/pytorch_geometric · dmlc/dgl · +5	2021
8	G_ResNet	79.90%	–	–		When Work Matters: Transforming Classical Network Structures to Graph CNN		2018
9	GCN	79.500±3.109	–	–		Semi-Supervised Classification with Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · tkipf/gcn · +52	2016
10	GraphGPS	79.250±3.096	–	–		Recipe for a General, Powerful, Scalable Graph Transformer	rampasek/GraphGPS · hamed1375/exphormer · graphcore/ogb-lsc-pcqm4mv2 · +1	2022
11	DUGNN	78.70%	–	–	✓	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning	vermaMachineLearning/Universal-Graph-Embedding-Neural-Network	2019
12	TFGW ADJ (L=2)	78.3%	–	–		Template based Graph Neural Network with Optimal Transport Distances	cedricvincentcuaz/TFGW	2022
13	PNA	78.000±3.808	–	–		Principal Neighbourhood Aggregation for Graph Nets	rusty1s/pytorch_geometric · dmlc/dgl · lukecavabarrett/pna · +5	2020
14	sGIN	77.94%	–	–		Mutual Information Maximization in Graph Neural Networks	CODE-SUBMIT/Graph_Neighborhood_1 · CODE-SUBMIT/Neighborhood-Enlargement-in-Graph-Network	2019
15	Graphormer	77.500±2.646	–	–		Do Transformers Really Perform Bad for Graph Representation?	microsoft/Graphormer · Microsoft/Graphormer · dpstart/graphormer_new · +2	2021
16	SEG-BERT	77.2%	–	–		Segmented Graph-Bert for Graph Instance Modeling	jwzhanggy/SEG-BERT	2020
17	U2GNN	77.04%	–	–		Universal Graph Transformer Self-Attention Networks	daiquocnguyen/Graph-Transformer	2019
18	PIN	76.6%	–	–		Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes		2023
19	GIUNet	76%	–	–		Graph isomorphism UNet	aramiracle/GIUNet	2023
20	Deep WL SGN(0,1,2)	75.70%	–	–		Subgraph Networks with Application to Structural Feature Space Expansion		2019