Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.03949 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917384164474880 |
|---|---|
| author | Ju, Clark Mingxuan Zhao, Tong Neves, Leonardo Collins, Liam Kumar, Bhuvesh Ren, Jiwen Zhang, Lili Zhuo, Wenfeng Zhang, Vincent Bai, Xiao Li, Jinchao Iyer, Karthik Fan, Zihao Xu, Yilun Chen, Yiwen Yu, Peicheng Malik, Manish Shah, Neil |
| author_facet | Ju, Clark Mingxuan Zhao, Tong Neves, Leonardo Collins, Liam Kumar, Bhuvesh Ren, Jiwen Zhang, Lili Zhuo, Wenfeng Zhang, Vincent Bai, Xiao Li, Jinchao Iyer, Karthik Fan, Zihao Xu, Yilun Chen, Yiwen Yu, Peicheng Malik, Manish Shah, Neil |
| contents | Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking. IDs can encode collaborative filtering signals within training data, such that RecSys models can extrapolate during the inference and personalize the prediction based on users' behavioral histories. Recently, Semantic IDs (SIDs) have become a trending paradigm for RecSys. In comparison to the conventional atomic ID, an SID is an ordered list of codes, derived from tokenizers such as residual quantization, applied to semantic representations commonly extracted from foundation models or collaborative signals. SIDs have drastically smaller cardinality than the atomic counterpart, and induce semantic clustering in the ID space. At Snapchat, we apply SIDs as auxiliary features for ranking models, and also explore SIDs as additional retrieval sources in different ML applications. In this paper, we discuss practical technical challenges we encountered while applying SIDs, experiments we have conducted, and design choices we have iterated to mitigate these challenges. Backed by promising offline results on both internal data and academic benchmarks as well as online A/B studies, SID variants have been launched in multiple production models with positive metrics impact. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03949 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices Ju, Clark Mingxuan Zhao, Tong Neves, Leonardo Collins, Liam Kumar, Bhuvesh Ren, Jiwen Zhang, Lili Zhuo, Wenfeng Zhang, Vincent Bai, Xiao Li, Jinchao Iyer, Karthik Fan, Zihao Xu, Yilun Chen, Yiwen Yu, Peicheng Malik, Manish Shah, Neil Information Retrieval Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking. IDs can encode collaborative filtering signals within training data, such that RecSys models can extrapolate during the inference and personalize the prediction based on users' behavioral histories. Recently, Semantic IDs (SIDs) have become a trending paradigm for RecSys. In comparison to the conventional atomic ID, an SID is an ordered list of codes, derived from tokenizers such as residual quantization, applied to semantic representations commonly extracted from foundation models or collaborative signals. SIDs have drastically smaller cardinality than the atomic counterpart, and induce semantic clustering in the ID space. At Snapchat, we apply SIDs as auxiliary features for ranking models, and also explore SIDs as additional retrieval sources in different ML applications. In this paper, we discuss practical technical challenges we encountered while applying SIDs, experiments we have conducted, and design choices we have iterated to mitigate these challenges. Backed by promising offline results on both internal data and academic benchmarks as well as online A/B studies, SID variants have been launched in multiple production models with positive metrics impact. |
| title | Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.03949 |