OptInter-M

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

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
LogLoss· 2021-08-03
0.3638
best: 0.3637 (OptInter)
SOTA
Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction arXiv:2108.01265
Click-Through Rate PredictiononiPinYou
LogLoss· 2021-08-03
0.00564
best: 0.005535 (FCN)
SOTA
Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction arXiv:2108.01265
Click-Through Rate PredictiononAvazu
AUC· 2021-08-03
0.806
best: 0.8062 (OptInter)
Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction arXiv:2108.01265
Click-Through Rate PredictiononiPinYou
AUC· 2021-08-03
0.78
best: 0.8174 (OPNN)
Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction arXiv:2108.01265