MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909948160507904 |
|---|---|
| author | Wu, Bin Yang, Feifan Chan, Zhangming Gu, Yu-Ran Feng, Jiawei Yi, Chao Sheng, Xiang-Rong Zhu, Han Xu, Jian Ye, Mang Zheng, Bo |
| author_facet | Wu, Bin Yang, Feifan Chan, Zhangming Gu, Yu-Ran Feng, Jiawei Yi, Chao Sheng, Xiang-Rong Zhu, Han Xu, Jian Ye, Mang Zheng, Bo |
| contents | Lifelong user interest modeling is crucial for industrial recommender systems, yet existing approaches rely predominantly on ID-based features, suffering from poor generalization on long-tail items and limited semantic expressiveness. While recent work explores multimodal representations for behavior retrieval in the General Search Unit (GSU), they often neglect multimodal integration in the fine-grained modeling stage -- the Exact Search Unit (ESU). In this work, we present a systematic analysis of how to effectively leverage multimodal signals across both stages of the two-stage lifelong modeling framework. Our key insight is that simplicity suffices in the GSU: lightweight cosine similarity with high-quality multimodal embeddings outperforms complex retrieval mechanisms. In contrast, the ESU demands richer multimodal sequence modeling and effective ID-multimodal fusion to unlock its full potential. Guided by these principles, we propose MUSE, a simple yet effective multimodal search-based framework. MUSE has been deployed in Taobao display advertising system, enabling 100K-length user behavior sequence modeling and delivering significant gains in top-line metrics with negligible online latency overhead. To foster community research, we share industrial deployment practices and open-source the first large-scale dataset featuring ultra-long behavior sequences paired with high-quality multimodal embeddings. Our code and data is available at https://taobao-mm.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07216 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling Wu, Bin Yang, Feifan Chan, Zhangming Gu, Yu-Ran Feng, Jiawei Yi, Chao Sheng, Xiang-Rong Zhu, Han Xu, Jian Ye, Mang Zheng, Bo Information Retrieval Machine Learning Lifelong user interest modeling is crucial for industrial recommender systems, yet existing approaches rely predominantly on ID-based features, suffering from poor generalization on long-tail items and limited semantic expressiveness. While recent work explores multimodal representations for behavior retrieval in the General Search Unit (GSU), they often neglect multimodal integration in the fine-grained modeling stage -- the Exact Search Unit (ESU). In this work, we present a systematic analysis of how to effectively leverage multimodal signals across both stages of the two-stage lifelong modeling framework. Our key insight is that simplicity suffices in the GSU: lightweight cosine similarity with high-quality multimodal embeddings outperforms complex retrieval mechanisms. In contrast, the ESU demands richer multimodal sequence modeling and effective ID-multimodal fusion to unlock its full potential. Guided by these principles, we propose MUSE, a simple yet effective multimodal search-based framework. MUSE has been deployed in Taobao display advertising system, enabling 100K-length user behavior sequence modeling and delivering significant gains in top-line metrics with negligible online latency overhead. To foster community research, we share industrial deployment practices and open-source the first large-scale dataset featuring ultra-long behavior sequences paired with high-quality multimodal embeddings. Our code and data is available at https://taobao-mm.github.io. |
| title | MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2512.07216 |