Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/GPS

GPS

Reported on 17 benchmarks across 5 tasks · 1 paper · 5 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Graphs15 results

Graph Property Predictiononogbg-molhiv
Test ROC-AUC· 2022-05-25
0.788
SOTA
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph Property Predictiononogbg-code2
Test F1 score· 2022-05-25
0.1894
SOTA
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph Property Predictiononogbg-ppa
Number of params· 2022-05-25
3434533
best: 16346166 (PAS+F2GNN)
SOTA
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph Property Predictiononogbg-ppa
Test Accuracy· 2022-05-25
0.8015
SOTA
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph Property Predictiononogbg-molpcba
Test AP· 2022-05-25
0.2907
SOTA
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph RegressiononPCQM4Mv2-LSC
Test MAE· 2022-05-25
0.0862
best: 0.0683 (EGT + Triangular Attention)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph RegressiononPCQM4Mv2-LSC
Validation MAE· 2022-05-25
0.0852
best: 0.0235 (ESA (Edge set attention, no positional encodings))
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph RegressiononZINC-500k
MAE· 2022-05-25
0.07
best: 0.051 (ESA + rings + NodeRWSE + EdgeRWSE)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph ClassificationonMNIST
Accuracy· 2022-05-25
98.05
best: 98.423 (CKGCN)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph ClassificationonCIFAR10 100k
Accuracy (%)· 2022-05-25
72.298
best: 76.468 (GRIT)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Node ClassificationonPATTERN
Accuracy· 2022-05-25
86.685
best: 88.661 (CKGCN)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Node ClassificationonCLUSTER
Accuracy· 2022-05-25
77.95
best: 80.026 (GRIT)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph Property Predictiononogbg-molhiv
Number of params· 2022-05-25
558625
best: 47183040 (Graphormer)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph Property Predictiononogbg-code2
Number of params· 2022-05-25
12454066
best: 63684290 (GMAN+bag of tricks)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
Graph Property Predictiononogbg-molpcba
Number of params· 2022-05-25
9744496
best: 119529665 (HIG(pre-trained on PCQM4M))
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454

Methodology2 results

ClassificationonMNIST
Accuracy· 2022-05-25
98.05
best: 98.423 (CKGCN)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454
ClassificationonCIFAR10 100k
Accuracy (%)· 2022-05-25
72.298
best: 76.468 (GRIT)
Recipe for a General, Powerful, Scalable Graph Transformer arXiv:2205.12454