DeepLight

Reported on 2 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.

Miscellaneous2 results

Click-Through Rate PredictiononCriteo
AUC· 2020-02-17
0.8123
best: 0.8163 (QNN-α)
SOTA
DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving arXiv:2002.06987
Click-Through Rate PredictiononCriteo
Log Loss· 2020-02-17
0.4395
best: 0.4358 (QNN-α)
SOTA
DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving arXiv:2002.06987