Mosaic shows that a fleet of four heterogeneous user-embedding specialists, trained with redundancy-reduction and composite-label losses, improves downstream recommendation quality at Meta.
hub
Title resolution pending
1 Pith paper cite this work, alongside 1,292 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1,292
external citations · OpenAlex
hub tools
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mosaic: A Fleet of User Embedding Specialists for Recommendation at Meta
Mosaic shows that a fleet of four heterogeneous user-embedding specialists, trained with redundancy-reduction and composite-label losses, improves downstream recommendation quality at Meta.