AI 中文总结
针对多模态序列推荐中用户偏好异质性与数据集模态偏差问题，提出即插即用的SG-UMP框架，通过模块组合器与模块路由器适配不同场景，在四个数据集上持续提升推荐性能。
AI 中文摘要
多模态序列推荐（Multimodal Sequential Recommendation, MSR）通过整合文本、图像、用户交互等异构信息提升推荐效果，但现有MSR方法常无法捕捉用户层面的偏好异质性与数据集层面的模态偏差，限制了其在不同用户和数据集间的适应性。为解决该问题，本文提出序列引导通用多模态优先级计算框架（Sequence-Guided Universal Multimodal Prioritization Calculation Framework, SG-UMP），这是一款用于增强MSR中多模态信息处理的即插即用插件。SG-UMP包含用于灵活多模态处理的模块组合器（Module Combiner）与用于动态模块排序的模块路由器（Module Router），可适配用户偏好与数据集特征。在四个真实世界数据集上的实验表明，SG-UMP在不同骨干网络与多模态设置下均能持续提升推荐性能，代码可在指定URL获取。
英文摘要
Multimodal sequential recommendation (MSR) improves recommendation by incorporating heterogeneous information such as text, images, and user interactions. However, existing MSR methods often fail to capture user-level preference heterogeneity and dataset-level modality bias, limiting their adaptability across users and datasets. To address this issue, we propose \textbf{S}equence-\textbf{G}uided \textbf{U}niversal \textbf{M}ultimodal \textbf{P}rioritization Calculation Framework (\textbf{SG-UMP}), a plug-and-play plugin for enhancing multimodal information processing in MSR. SG-UMP includes a Module Combiner for flexible multimodal processing and a Module Router for dynamic module ordering, enabling adaptation to both user preferences and dataset characteristics. Experiments on four real-world datasets show that SG-UMP consistently improves recommendation performance across different backbones and multimodal settings. The code is available at https://github.com/esemsc-xz524/SG-UMP .
CommentsAccepted as a Full Paper at MM 2026
