Recommender Systems with Generative Retrieval
Preprint
Abstract
Modern recommender systems leverage large-scale retrieval models consisting of two stages: training a dual-encoder model to embed queries and candidates in the same space, followed by an Approximate Nearest Neighbor (ANN) search to select top candidates given a query's embedding. In this paper, we propose a new single-stage paradigm: a generative retrieval model which autoregressively decodes the identifiers for the target candidates in one phase. To do this, instead of assigning randomly generated atomic IDs to each item, we generate Semantic IDs: a semantically meaningful tuple of codewords for each item that serves as its unique identifier. We use a hierarchical method called RQ-VAE to generate these codewords. Once we have the Semantic IDs for all the items, a Transformer based sequence-to-sequence model is trained to predict the Semantic ID of the next item. Since this model predicts the tuple of codewords identifying the next item directly in an autoregressive manner, it can be considered a generative retrieval model. We show that our recommender system trained in this new paradigm improves the results achieved by current SOTA models on the Amazon dataset. Moreover, we demonstrate that the sequence-to-sequence model coupled with hierarchical Semantic IDs offers better generalization and hence improves retrieval of cold-start items for recommendations.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited2023
- Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders2023
- SoundStream: An End-to-End Neural Audio CodecIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- Learning to Embed Categorical Features without Embedding Tables for Recommendation2021
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- Neural Machine Translation of Rare Words with Subword Units2016
- Product Quantization for Nearest Neighbor SearchIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009