A per-user distilled MLP, fine-tuned with triplet loss on recent interactions, enables 1.5 ms CPU fashion recommendations with 700 KB memory per shopper.
Neural Networks129, 203–221 (2020)
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
-
Real-time and personalized product recommendations for large e-commerce platforms
A per-user distilled MLP, fine-tuned with triplet loss on recent interactions, enables 1.5 ms CPU fashion recommendations with 700 KB memory per shopper.