Skip to yearly menu bar Skip to main content


Recommender Systems with Generative Retrieval

Shashank Rajput · Nikhil Mehta · Anima Singh · Raghunandan Hulikal Keshavan · Trung Vu · Lukasz Heldt · Lichan Hong · Yi Tay · Vinh Tran · Jonah Samost · Maciej Kula · Ed Chi · Maheswaran Sathiamoorthy

Great Hall & Hall B1+B2 (level 1) #604
[ ]
[ Paper [ Poster [ OpenReview
Tue 12 Dec 3:15 p.m. PST — 5:15 p.m. PST


Modern recommender systems perform large-scale retrieval by embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this paper, we propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful tuple of codewords to serve as a Semantic ID for each item. Given Semantic IDs for items in a user session, a Transformer-based sequence-to-sequence model is trained to predict the Semantic ID of the next item that the user will interact with. We show that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets. In addition, we show that incorporating Semantic IDs into the sequence-to-sequence model enhances its ability to generalize, as evidenced by the improved retrieval performance observed for items with no prior interaction history.

Chat is not available.