FeSAIL combines staleness-weighted maximum coverage sampling with a staleness-scaled embedding-update regularizer, improving incremental CTR prediction by 0.3% to 1.7% AUC over baselines on four datasets.
Real- time top-n recommendation in social streams
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Feature Staleness Aware Incremental Learning for CTR Prediction
FeSAIL combines staleness-weighted maximum coverage sampling with a staleness-scaled embedding-update regularizer, improving incremental CTR prediction by 0.3% to 1.7% AUC over baselines on four datasets.