Node Classification on Cora

73개 결과 · ⬇ CSV · JSON

Accuracy

Rank	Model	Accuracy	Training Split	Validation	1:1 Accuracy	Inference Time (ms)	Extra Training Data	Paper	Code	Year
1	SSP	90.16% ± 0.59%	–	–	–	–		Optimization of Graph Neural Networks with Natural Gradient Descent	russellizadi/ssp	2020
2	SplineCNN	89.48% ± 0.31%	–	–	–	–		SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels	rusty1s/pytorch_geometric · rusty1s/pytorch_spline_conv · abhilash1910/SpectralEmbeddings · +2	2017
3	ACMII-Snowball-3	89.36% ± 1.26%	–	–	–	–		Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?		2021
4	ACMII-GCN	88.95% ± 1.04%	–	–	–	–		Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?		2021
5	ACM-Snowball-2	88.83% ± 1.49%	–	–	–	–		Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?		2021
6	UGT	88.74±0.6%	–	–	–	–		Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity	nslab-cuk/unified-graph-transformer · nslab-cuk/community-aware-graph-transformer · nslab-cuk/literalkg	2023
7	GAT + SWA	88.66 ± 1.38%	–	–	–	–		The Split Matters: Flat Minima Methods for Improving the Performance of GNNs	foisunt/fmms-in-gnns	2023
8	ACM-GCN	88.62% ± 1.22%	–	–	–	–		Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?		2021
9	GCN-LPA	88.5% ± 1.5%	–	–	–	–		Unifying Graph Convolutional Neural Networks and Label Propagation	hwwang55/GCN-LPA · achalagarwal/gcn-lpa	2020
10	LinkDist	88.24%	–	–	–	–		Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages	cf020031308/LinkDist · cf020031308/LinkDist	2021
11	CNMPGNN	88.20±1.22%	–	–	–	–		CN-Motifs Perceptive Graph Neural Networks		2021
12	CoLinkDist	87.89%	–	–	–	–		Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages	cf020031308/LinkDist · cf020031308/LinkDist	2021
13	3ference	87.78%	–	–	–	–		Inferring from References with Differences for Semi-Supervised Node Classification on Graphs	cf020031308/3ference	2022
14	LinkDistMLP	87.58%	–	–	–	–		Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages	cf020031308/LinkDist · cf020031308/LinkDist	2021
15	CoLinkDistMLP	87.54%	–	–	–	–		Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages	cf020031308/LinkDist · cf020031308/LinkDist	2021
16	AS-GCN	87.44% ± 0.0034%	–	–	–	–	✓	Adaptive Sampling Towards Fast Graph Representation Learning	dmlc/dgl · huangwb/AS-GCN	2018
17	CGT	87.10±1.53	–	–	–	–		Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures	nslab-cuk/community-aware-graph-transformer	2023
18	NodeNet	86.80%	–	–	–	–		NodeNet: A Graph Regularised Neural Network for Node Classification		2020
18	Cleora	86.80%	–	–	–	–		Cleora: A Simple, Strong and Scalable Graph Embedding Scheme	Synerise/cleora · Synerise/booking-challenge	2021
20	DFNet-ATT	86% ± 0.4%	–	–	–	–		DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters	wokas36/DFNets	2019