A mixture-of-experts fusion of trainable LLM semantic embeddings with collaborative item IDs, followed by universal-then-targeted pre-training, improves sequential recommendation on Amazon and WeChat.
Actions speak louder than words: Trillion- parameter sequential transducers for generative recommendations,
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
PRECISE: Pre-training Sequential Recommenders with Collaborative and Semantic Information
A mixture-of-experts fusion of trainable LLM semantic embeddings with collaborative item IDs, followed by universal-then-targeted pre-training, improves sequential recommendation on Amazon and WeChat.