Graph Regression On Peptides Struct

Metrics

MAE

Results

Performance results of various models on this benchmark

Model Name	MAE	Paper Title	Repository
DRew-GCN+LapPE	0.2536±0.0015	DRew: Dynamically Rewired Message Passing with Delay
Graph Diffuser	0.2461±0.0010	Diffusing Graph Attention	-
CIN++-500k	0.2523	CIN++: Enhancing Topological Message Passing
GatedGCN-tuned	0.2477±0.0009	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
BoP	0.25	From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis
Exphormer	0.2481±0.0007	Exphormer: Sparse Transformers for Graphs
ViT-PS	0.2559	Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
TokenGT	0.2489±0.0013	Pure Transformers are Powerful Graph Learners
RDKit + LightGBM	0.2459	Molecular Fingerprints Are Strong Models for Peptide Function Prediction
NPQ+GATv2	0.2589±0.0031	Neural Priority Queues for Graph Neural Networks	-
NeuralWalker	0.2463 ± 0.0005	Learning Long Range Dependencies on Graphs via Random Walks
ECFP + LightGBM	0.2432	Molecular Fingerprints Are Strong Models for Peptide Function Prediction
GCN-tuned	0.2460±0.0007	Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
Transformer+LapPE	0.2529±0.0016	Long Range Graph Benchmark
SAN+LapPE	0.2683±0.0043	Long Range Graph Benchmark
EIGENFORMER	0.2599	Graph Transformers without Positional Encodings	-
ESA + RWSE (Edge set attention, Random Walk Structural Encoding, tuned)	0.2393±0.0004	An end-to-end attention-based approach for learning on graphs	-
GCN	0.3496±0.0013	Long Range Graph Benchmark
GPS	0.2500±0.0005	Recipe for a General, Powerful, Scalable Graph Transformer
GraphMLPMixer	0.2475±0.0015	A Generalization of ViT/MLP-Mixer to Graphs

0 of 39 row(s) selected.