Graph Regression On Peptides Struct

MAE

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
GINE	0.3547±0.0045	Long Range Graph Benchmark
GCN	0.3496±0.0013	Long Range Graph Benchmark
GCNII	0.3471±0.0010	Simple and Deep Graph Convolutional Networks
GatedGCN	0.3420±0.0013	Long Range Graph Benchmark
GatedGCN+RWSE	0.3357±0.0006	Long Range Graph Benchmark
GCN + PANDA	0.3272±0.0001	PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
SAN+LapPE	0.2683±0.0043	Long Range Graph Benchmark
EIGENFORMER	0.2599	Graph Transformers without Positional Encodings
NPQ+GATv2	0.2589±0.0031	Neural Priority Queues for Graph Neural Networks
ViT-PS	0.2559	Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
PathNN	0.2545±0.0032	Path Neural Networks: Expressive and Accurate Graph Neural Networks
SAN+RWSE	0.2545±0.0012	Long Range Graph Benchmark
DRew-GCN+LapPE	0.2536±0.0015	DRew: Dynamically Rewired Message Passing with Delay
Transformer+LapPE	0.2529±0.0016	Long Range Graph Benchmark
CIN++-500k	0.2523	CIN++: Enhancing Topological Message Passing
GPS-tuned	0.2509±0.0014	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
BoP	0.25	From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis
GPS	0.2500±0.0005	Recipe for a General, Powerful, Scalable Graph Transformer
TokenGT	0.2489±0.0013	Pure Transformers are Powerful Graph Learners
GCN+virtual node	0.2488±0.0021	On the Connection Between MPNN and Graph Transformer

0 of 39 row(s) selected.