Fi-GNN

Reported on 4 benchmarks across 1 task · 1 paper

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

Miscellaneous4 results

Click-Through Rate PredictiononAvazu
AUC· 2019-10-12
0.7762
best: 0.8062 (OptInter)
Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction arXiv:1910.05552
Click-Through Rate PredictiononAvazu
LogLoss· 2019-10-12
0.3825
best: 0.3637 (OptInter)
Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction arXiv:1910.05552
Click-Through Rate PredictiononCriteo
AUC· 2019-10-12
0.8062
best: 0.8163 (QNN-α)
Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction arXiv:1910.05552
Click-Through Rate PredictiononCriteo
Log Loss· 2019-10-12
0.4453
best: 0.4358 (QNN-α)
Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction arXiv:1910.05552