Adding low-weight noisy copies of training examples improves Meta's ads ranking by about 0.1% to 0.3% relative Normalized Entropy, and slightly outperforms self-consistency regularization.
Samarth Sinha and Adji Bousso Dieng
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking
Adding low-weight noisy copies of training examples improves Meta's ads ranking by about 0.1% to 0.3% relative Normalized Entropy, and slightly outperforms self-consistency regularization.