Two-Tower Architecture: The Two Networks Behind Every Feed
Summary
You cannot run a big model a billion times per request, so recommenders split it: a user tower and an item tower embed into the same vector space, trained contrastively on clicks, meeting only at a dot product. Item vectors are precomputed offline into an ANN index; one query-tower pass returns hundreds of candidates from millions in milliseconds (YouTube's candidate-generation design), and a heavy reranker scores just that shortlist. The trade is fine-grained query-item interaction, which rerankers and late-interaction models recover downstream. Explore: mixpeek.com/diagrams/muvera-two-tier-retrieval
About this video
You cannot run a big model a billion times per request, so recommenders split it: a user tower and an item tower embed into the same vector space, trained contrastively on clicks, meeting only at a dot product. Item vectors are precomputed offline into an ANN index; one query-tower pass returns hundreds of candidates from millions in milliseconds (YouTube's candidate-generation design), and a heavy reranker scores just that shortlist. The trade is fine-grained query-item interaction, which rerankers and late-interaction models recover downstream. Explore: mixpeek.com/diagrams/muvera-two-tier-retrieval