Graph Classification On Peptides Func

评估指标

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
ESA + RWSE (Edge set attention, Random Walk Structural Encoding, + validation set)	0.7479	An end-to-end attention-based approach for learning on graphs
ECFP + LightGBM	0.7460	Molecular Fingerprints Are Strong Models for Peptide Function Prediction
ESA + RWSE (Edge set attention, Random Walk Structural Encoding, tuned)	0.7357±0.0036	An end-to-end attention-based approach for learning on graphs
TT + LightGBM	0.7318	Molecular Fingerprints Are Strong Models for Peptide Function Prediction
S²GCN	0.7311±0.0066	Spatio-Spectral Graph Neural Networks
RDKit + LightGBM	0.7311	Molecular Fingerprints Are Strong Models for Peptide Function Prediction
GCN+	0.7261 ± 0.0067	Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
GraphGPS + HDSE	0.7156±0.0058	Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
DRew-GCN+LapPE	0.7150±0.0044	DRew: Dynamically Rewired Message Passing with Delay
GRED+LapPE	0.7133±0.0011	Recurrent Distance Filtering for Graph Representation Learning
NeuralWalker	0.7096 ± 0.0078	Learning Long Range Dependencies on Graphs via Random Walks
GRED	0.7085±0.0027	Recurrent Distance Filtering for Graph Representation Learning
ESA (Edge set attention, no positional encodings, tuned)	0.7071±0.0015	An end-to-end attention-based approach for learning on graphs
GRIT	0.6988±0.0082	Graph Inductive Biases in Transformers without Message Passing
CKGCN	0.6952	CKGConv: General Graph Convolution with Continuous Kernels
Graph ViT	0.6942±0.0075	A Generalization of ViT/MLP-Mixer to Graphs
GraphMLPMixer	0.6921±0.0054	A Generalization of ViT/MLP-Mixer to Graphs
GatedGCN-HSG	0.6866±0.0038	Next Level Message-Passing with Hierarchical Support Graphs
ESA (Edge set attention, no positional encodings, not tuned)	0.6863±0.0044	An end-to-end attention-based approach for learning on graphs
GCN-tuned	0.6860±0.0050	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark

0 of 44 row(s) selected.