{"ID":2887630,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01375","arxiv_id":"2508.01375","title":"SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation","abstract":"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.","short_abstract":"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 representatio...","url_abs":"https://arxiv.org/abs/2508.01375","url_pdf":"https://arxiv.org/pdf/2508.01375v1","authors":"[\"Yining Yao\",\"Ziwei Li\",\"Shuwen Xiao\",\"Boya Du\",\"Jialin Zhu\",\"Junjun Zheng\",\"Xiangheng Kong\",\"Yuning Jiang\"]","published":"2025-08-02T14:09:21Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false}