提出可插拔的多模态推荐框架，动态适配用户与数据集差异。
SG-UMP: Sequence-Guided Universal Multimodal Prioritization Calculation Framework
- 通过模块组合器与路由器实现多模态信息灵活处理
- 在四个真实数据集上提升不同模型与设置下的推荐效果
- 适合需要自适应多模态融合的推荐系统研究者
多模态序列推荐（MSR）通过整合文本、图像和用户行为等异构信息提升推荐效果。然而，现有方法常难以捕捉用户层面偏好差异和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。为此，我们提出序列引导的通用多模态优先级计算框架（SG-UMP），作为增强MSR中多模态信息处理的即插即用插件。SG-UMP包含模块组合器以实现灵活的多模态处理，以及模块路由器以动态调整模块顺序，从而适应用户偏好与数据集特性。在四个真实世界数据集上的实验表明，SG-UMP在不同主干模型和多模态设置下均能持续提升推荐性能。代码已开源：https://github.com/esemsc-xz524/SG-UMP。
原文摘要 · Abstract (English)
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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。