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/AutoInt

AutoInt

Reported on 8 benchmarks across 1 task · 1 paper · 6 SOTA

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

Miscellaneous8 results

Click-Through Rate PredictiononAvazu
AUC· 2018-10-29
0.7752
best: 0.8062 (OptInter)
SOTA
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921
Click-Through Rate PredictiononAvazu
LogLoss· 2018-10-29
0.3823
best: 0.3637 (OptInter)
SOTA
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921
Click-Through Rate PredictiononMovieLens 1M
Log Loss· 2018-10-29
0.3784
best: 0.2016 (STEC)
SOTA
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921
Click-Through Rate PredictiononCriteo
AUC· 2018-10-29
0.8061
best: 0.8163 (QNN-α)
SOTA
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921
Click-Through Rate PredictiononKDD12
AUC· 2018-10-29
0.7881
best: 0.8098 (FCN)
SOTA
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921
Click-Through Rate PredictiononKDD12
Log Loss· 2018-10-29
0.1545
best: 0.1494 (FCN)
SOTA
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921
Click-Through Rate PredictiononMovieLens 1M
AUC· 2018-10-29
0.846
best: 0.9712 (STEC)
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921
Click-Through Rate PredictiononCriteo
Log Loss· 2018-10-29
0.4454
best: 0.4358 (QNN-α)
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks arXiv:1810.11921