HyperAI超神経

プラットフォーム

Node Classification On Coco Sp

評価指標

macro F1

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
NeuralWalker	0.4398 ± 0.0033	Learning Long Range Dependencies on Graphs via Random Walks
GPS-tuned	0.3884±0.0055	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
GatedGCN+	0.3802 ± 0.0015	Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
GatedGCN-HSG	0.3535±0.0032	Next Level Message-Passing with Hierarchical Support Graphs
Exphormer	0.343±0.0008	Exphormer: Sparse Transformers for Graphs
GPS	0.3412±0.0044	Recipe for a General, Powerful, Scalable Graph Transformer
GatedGCN-tuned	0.2922±0.0018	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
GatedGCN	0.2641±0.0045	Long Range Graph Benchmark
Transformer+LapPE	0.2618±0.0031	Long Range Graph Benchmark
SAN+LapPE	0.2592±0.0158	Long Range Graph Benchmark
GatedGCN+LapPE	0.2574±0.0034	Long Range Graph Benchmark
SAN+RWSE	0.2434±0.0156	Long Range Graph Benchmark
GINE-tuned	0.2125±0.0009	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
GCNII	0.1404±0.0011	Simple and Deep Graph Convolutional Networks
GINE	0.1339±0.0044	Long Range Graph Benchmark
GCN-tuned	0.1338±0.0007	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
GCN	0.0841±0.0010	Long Range Graph Benchmark

0 of 17 row(s) selected.