SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912516462870528 |
|---|---|
| author | Yao, Yining Li, Ziwei Xiao, Shuwen Du, Boya Zhu, Jialin Zheng, Junjun Kong, Xiangheng Jiang, Yuning |
| author_facet | Yao, Yining Li, Ziwei Xiao, Shuwen Du, Boya Zhu, Jialin Zheng, Junjun Kong, Xiangheng Jiang, Yuning |
| contents | In recommendation systems, predicting Click-Through Rate (CTR) is crucial for accurately matching users with items. To improve recommendation performance for cold-start and long-tail items, recent studies focus on leveraging item multimodal features to model users' interests. However, obtaining multimodal representations for items relies on complex pre-trained encoders, which incurs unacceptable computation cost to train jointly with downstream ranking models. Therefore, it is important to maintain alignment between semantic and behavior space in a lightweight way.
To address these challenges, we propose a Semantic-Behavior Alignment for Cold-start Recommendation framework, which mainly focuses on utilizing multimodal representations that align with the user behavior space to predict CTR. First, we leverage domain-specific knowledge to train a multimodal encoder to generate behavior-aware semantic representations. Second, we use residual quantized semantic ID to dynamically bridge the gap between multimodal representations and the ranking model, facilitating the continuous semantic-behavior alignment. We conduct our offline and online experiments on the Taobao, one of the world's largest e-commerce platforms, and have achieved an increase of 0.83% in offline AUC, 13.21% clicks increase and 13.44% orders increase in the online A/B test, emphasizing the efficacy of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01375 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation Yao, Yining Li, Ziwei Xiao, Shuwen Du, Boya Zhu, Jialin Zheng, Junjun Kong, Xiangheng Jiang, Yuning Information Retrieval In recommendation systems, predicting Click-Through Rate (CTR) is crucial for accurately matching users with items. To improve recommendation performance for cold-start and long-tail items, recent studies focus on leveraging item multimodal features to model users' interests. However, obtaining multimodal representations for items relies on complex pre-trained encoders, which incurs unacceptable computation cost to train jointly with downstream ranking models. Therefore, it is important to maintain alignment between semantic and behavior space in a lightweight way. To address these challenges, we propose a Semantic-Behavior Alignment for Cold-start Recommendation framework, which mainly focuses on utilizing multimodal representations that align with the user behavior space to predict CTR. First, we leverage domain-specific knowledge to train a multimodal encoder to generate behavior-aware semantic representations. Second, we use residual quantized semantic ID to dynamically bridge the gap between multimodal representations and the ranking model, facilitating the continuous semantic-behavior alignment. We conduct our offline and online experiments on the Taobao, one of the world's largest e-commerce platforms, and have achieved an increase of 0.83% in offline AUC, 13.21% clicks increase and 13.44% orders increase in the online A/B test, emphasizing the efficacy of our method. |
| title | SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2508.01375 |