Generative pretraining plus sparse-embedding freezing makes large Transformer ranking models scale consistently, following a power law from 13K to 0.3B dense parameters.
Title resolution pending
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
-
Scaling Transformers for Discriminative Recommendation via Generative Pretraining
Generative pretraining plus sparse-embedding freezing makes large Transformer ranking models scale consistently, following a power law from 13K to 0.3B dense parameters.