SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling
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_ | 1866918521386041344 |
|---|---|
| author | Zhang, Yaqian Yu, Ruyi Li, Tianyi Liu, Bohan Ye, Maoquan Wang, Ke Wen, Shifeng Pan, Junwei Wang, Lijie Zhou, Qi Cai, Yeshou Yin, Chengguo Wang, Lifeng Li, Hui Xiao, Lei Gu, Haijie |
| author_facet | Zhang, Yaqian Yu, Ruyi Li, Tianyi Liu, Bohan Ye, Maoquan Wang, Ke Wen, Shifeng Pan, Junwei Wang, Lijie Zhou, Qi Cai, Yeshou Yin, Chengguo Wang, Lifeng Li, Hui Xiao, Lei Gu, Haijie |
| contents | Industrial recommender systems increasingly leverage lifelong user behavior histories and rich multi-modal content to capture evolving user preferences. However, effectively integrating multi-modal features into lifelong interest modeling remains challenging due to the inherent misalignment between multi-modal and collaborative spaces. Existing paradigms typically rely on separate modeling of multi-modal sequence and behavior sequence, and late fusion to alleviate the modality gap, which results in coarse-grained multi-modal representation and limited integration. In this paper, we propose SIREN, a unified multi-granularity semantic interaction framework for multi-modal lifelong user interest modeling. In the General Search Unit stage, we introduce two alternative retrieval strategies: multi-modal similarity-based soft retrieval for retrieval effectiveness, and Semantic ID (SemID)-based hard retrieval for efficient industrial serving. For the Exact Search Unit stage, we explicitly incorporate target-aware relevance via coarse similarity buckets and fine-grained prefix-encoded SemIDs, enabling unified interaction with collaborative ID features within the target-conditioned transformer architecture. Extensive experiments on the offline dataset demonstrate that SIREN achieves a state-of-the-art GAUC. Online A/B tests further demonstrate consistent GMV gains across multiple production scenarios, including +2.28% in Weixin Moments, +3.87% in Weixin Official Accounts, and +1.61% in Weixin Channels. From July 2025, SIREN has been fully launched for full-traffic serving in Tencent's advertising platform. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25726 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling Zhang, Yaqian Yu, Ruyi Li, Tianyi Liu, Bohan Ye, Maoquan Wang, Ke Wen, Shifeng Pan, Junwei Wang, Lijie Zhou, Qi Cai, Yeshou Yin, Chengguo Wang, Lifeng Li, Hui Xiao, Lei Gu, Haijie Information Retrieval Industrial recommender systems increasingly leverage lifelong user behavior histories and rich multi-modal content to capture evolving user preferences. However, effectively integrating multi-modal features into lifelong interest modeling remains challenging due to the inherent misalignment between multi-modal and collaborative spaces. Existing paradigms typically rely on separate modeling of multi-modal sequence and behavior sequence, and late fusion to alleviate the modality gap, which results in coarse-grained multi-modal representation and limited integration. In this paper, we propose SIREN, a unified multi-granularity semantic interaction framework for multi-modal lifelong user interest modeling. In the General Search Unit stage, we introduce two alternative retrieval strategies: multi-modal similarity-based soft retrieval for retrieval effectiveness, and Semantic ID (SemID)-based hard retrieval for efficient industrial serving. For the Exact Search Unit stage, we explicitly incorporate target-aware relevance via coarse similarity buckets and fine-grained prefix-encoded SemIDs, enabling unified interaction with collaborative ID features within the target-conditioned transformer architecture. Extensive experiments on the offline dataset demonstrate that SIREN achieves a state-of-the-art GAUC. Online A/B tests further demonstrate consistent GMV gains across multiple production scenarios, including +2.28% in Weixin Moments, +3.87% in Weixin Official Accounts, and +1.61% in Weixin Channels. From July 2025, SIREN has been fully launched for full-traffic serving in Tencent's advertising platform. |
| title | SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2605.25726 |