DOS: Dual-Flow Orthogonal Semantic IDs for Recommendation in Meituan
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911421774692352 |
|---|---|
| author | Yin, Junwei Kou, Senjie Li, Changhao Wang, Shuli Wei, Xue Huang, Yinqiu Zhu, Yinhua Wang, Haitao Wang, Xingxing |
| author_facet | Yin, Junwei Kou, Senjie Li, Changhao Wang, Shuli Wei, Xue Huang, Yinqiu Zhu, Yinhua Wang, Haitao Wang, Xingxing |
| contents | Semantic IDs serve as a key component in generative recommendation systems. They not only incorporate open-world knowledge from large language models (LLMs) but also compress the semantic space to reduce generation difficulty. However, existing methods suffer from two major limitations: (1) the lack of contextual awareness in generation tasks leads to a gap between the Semantic ID codebook space and the generation space, resulting in suboptimal recommendations; and (2) suboptimal quantization methods exacerbate semantic loss in LLMs. To address these issues, we propose Dual-Flow Orthogonal Semantic IDs (DOS) method. Specifically, DOS employs a user-item dual flow-framework that leverages collaborative signals to align the Semantic ID codebook space with the generation space. Furthermore, we introduce an orthogonal residual quantization scheme that rotates the semantic space to an appropriate orientation, thereby maximizing semantic preservation. Extensive offline experiments and online A/B testing demonstrate the effectiveness of DOS. The proposed method has been successfully deployed in Meituan's mobile application, serving hundreds of millions of users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04460 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DOS: Dual-Flow Orthogonal Semantic IDs for Recommendation in Meituan Yin, Junwei Kou, Senjie Li, Changhao Wang, Shuli Wei, Xue Huang, Yinqiu Zhu, Yinhua Wang, Haitao Wang, Xingxing Information Retrieval Semantic IDs serve as a key component in generative recommendation systems. They not only incorporate open-world knowledge from large language models (LLMs) but also compress the semantic space to reduce generation difficulty. However, existing methods suffer from two major limitations: (1) the lack of contextual awareness in generation tasks leads to a gap between the Semantic ID codebook space and the generation space, resulting in suboptimal recommendations; and (2) suboptimal quantization methods exacerbate semantic loss in LLMs. To address these issues, we propose Dual-Flow Orthogonal Semantic IDs (DOS) method. Specifically, DOS employs a user-item dual flow-framework that leverages collaborative signals to align the Semantic ID codebook space with the generation space. Furthermore, we introduce an orthogonal residual quantization scheme that rotates the semantic space to an appropriate orientation, thereby maximizing semantic preservation. Extensive offline experiments and online A/B testing demonstrate the effectiveness of DOS. The proposed method has been successfully deployed in Meituan's mobile application, serving hundreds of millions of users. |
| title | DOS: Dual-Flow Orthogonal Semantic IDs for Recommendation in Meituan |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2602.04460 |