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.
Deep learning.nature, pages 436–44., 2015 May
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
-
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.