A duration-grouped, distribution-transformed multiplicative correction layer removes local watch-time prediction bias on top of frozen rankers, improving offline MAE/XAUC and online time spent.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
IEFF enables retrain-free feature efficiency rollouts in ranking systems by elastically controlling feature coverage at serving time, achieving 5x faster rollouts, zero retraining GPU cost, and 50-55% less performance degradation than abrupt feature removal.
citing papers explorer
-
DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems
A duration-grouped, distribution-transformed multiplicative correction layer removes local watch-time prediction bias on top of frozen rankers, improving offline MAE/XAUC and online time spent.
-
Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale
IEFF enables retrain-free feature efficiency rollouts in ranking systems by elastically controlling feature coverage at serving time, achieving 5x faster rollouts, zero retraining GPU cost, and 50-55% less performance degradation than abrupt feature removal.
- A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods