SplitGNN

Reported on 5 benchmarks across 3 tasks

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

Miscellaneous2 results

Fraud DetectiononYelp-Fraud
AUC-ROC
92.03
best: 96.4 (LEX-GNN)
Fraud DetectiononFDCompCN
AUC-ROC
68.98

Robots2 results

Active Speaker DetectiononYelp-Fraud
AUC-ROC
92.03
best: 96.4 (LEX-GNN)
Active Speaker DetectiononFDCompCN
AUC-ROC
68.98

Graphs1 result

Node ClassificationonYelp-Fraud
AUC-ROC
92.03
best: 96.4 (LEX-GNN)