List your company
ResearchFormerly WizWand

Node Classification on PATTERN (test)

87.281Test AccuracyGRIT
71.2764475.4314779.586583.74153Mar 26, 2021Jan 31, 2022Dec 8, 2022Oct 16, 2023Aug 22, 2024Jun 29, 2025May 7, 2026
Updated 4mo ago

Evaluation results

MethodLinks
GRITencoding=HDSE2023.0887.281
GRIT# Parameters=~ 500K2023.0587.196
GRIT2023.0887.196
GRITparameter budget=≈ 500K2023.1287.196
GRIT2024.0687.196
GRIT2026.0587.196
CSA2023.0487.011
NeuralWalker2024.0686.977
SATencoding=HDSE2023.0886.933
GIN-AK+2022.0586.85
GIN-AK+# Parameters=~ 500K2023.0586.85
GIN-AK+2023.0886.85
GIN-AK+2026.0586.85
K-Subgraph SAT2022.0586.848
SAT2023.0486.848
K-Subgraph SAT# Parameters=~ 500K2023.0586.848
SAT2023.0886.848
SATparameter budget=≈ 500K2023.1286.848
Graphormer2024.0686.848
EGT2022.0586.821
EGT2023.0486.821
EGT# Parameters=~ 500K2023.0586.821
Graphormer-GD2023.0886.821
EGTparameter budget=≈ 500K2023.1286.821
EGT2026.0586.821
GNASDepth=4, Parameters=0.35M, Search Cost=2.45 hr, Training Cost=2.15 hr2021.0386.8
GPS-GCCMBackbone=GPS2026.0586.772
GREDparameter budget=≈ 500K2023.1286.759
Graph ViT/MLP-Mixer2023.0886.742
GraphGPSencoding=HDSE2023.0886.737
GTencoding=HDSE2023.0886.713
Exphormer2024.0686.7
GPS-PCLBackbone=GPS2026.0586.695
TransformerComplexity=O(N^2), Positional Encoding=Baseline2025.0986.69
GPS2022.0586.685
GPS2023.0486.685
GPS# Parameters=~ 500K2023.0586.685
GraphGPS2023.0886.685
GPSparameter budget=≈ 500K2023.1286.685
GPS2024.0686.685
DGN2022.0586.68
DGN# Parameters=~ 500K2023.0586.68
DGN2026.0586.68
ViT-PSsamples=10, pretrain=ImageNet-21k2023.0686.65
GPS2026.0586.648
WIREModel Architecture=Performer, Complexity=O(N)2025.0986.63
SAN2022.0586.581
SAN2023.0486.581
SAN# Parameters=~ 500K2023.0586.581
SAN2023.0886.581
SANparameter budget=≈ 500K2023.1286.581
SAN2026.0586.581
ViT-PSsamples=1, pretrain=ImageNet-21k2023.0686.573
ViT-Canonicalpretrain=ImageNet-21k2023.0686.534
RingGNNlayers=22023.0686.245
ViT-PSsamples=10, pretrain=none2023.0685.989
ViT-PSsamples=1, pretrain=none2023.0685.868
ViT-Canonicalpretrain=none2023.0685.825
SINC-GCN2025.1185.79
SIR-GCN2025.1185.75
PerformerComplexity=O(N), Positional Encoding=Baseline2025.0985.71
GPS-LGDBackbone=GPS2026.0585.662
PPGNlayers=32023.0685.661
GCNlayers=162023.0685.614
GCNparameter budget=≈ 500K2023.1285.614
GINDepth=4, Parameters=0.10M, Training Cost=0.40 hr2021.0385.59
GINparameter budget=≈ 500K2023.1285.59
GIN2025.1185.59
GatedGCN2022.0585.568
GatedGCN# Parameters=~ 500K2023.0585.568
GatedGCNlayers=162023.0685.568
GatedGCN2023.0885.568
GatedGCNparameter budget=≈ 500K2023.1285.568
GatedGCN2024.0685.568
GatedGCN2026.0585.568
GCN2025.1185.5
MoNetDepth=4, Parameters=0.10M, Training Cost=0.90 hr2021.0385.48
GIN2022.0585.387
GIN# Parameters=~ 500K2023.0585.387
GINlayers=162023.0685.387
GIN2023.0885.387
GIN2024.0685.387
GIN2026.0585.387
SGFormer2023.0885.287
GraphNASDepth=4, Parameters=0.48M, Search Cost=120 hr, Training Cost=8.25 hr2021.0385.21
GT2023.0884.808
ViT-GAsamples=10, pretrain=ImageNet-21k2023.0684.641
GatedGCNDepth=4, Parameters=0.10M, Training Cost=3.09 hr2021.0384.48
ViT-GAsamples=10, pretrain=none2023.0683.22
ViT-GAsamples=1, pretrain=ImageNet-21k2023.0681.933
ViT-FApretrain=ImageNet-21k2023.0680.015
GAT2022.0578.271
GAT# Parameters=~ 500K2023.0578.271
GATparameter budget=≈ 500K2023.1278.271
GAT2024.0678.271
GAT2026.0578.271
GATlayers=162023.0678.221
ViT-GAsamples=1, pretrain=none2023.0676.956
GATDepth=4, Parameters=0.11M, Training Cost=0.57 hr2021.0375.82
GCN2022.0571.892