决策剖析：面向多模态推荐的不确定性感知分层意图学习流匹配方法
Anatomy of a Decision: Uncertainty-aware Hierarchical Intent Learning via Flow Matching for Multimodal Recommendation
查看机构详情
- Sydney Smart Technology College, Northeastern University（悉尼智能科技学院，东北大学）
- School of Computer and Communication Engineering and Hebei Key Laboratory of Marine Perception Network and Data Processing, Northeastern University at Qinhuangdao（秦皇岛东北大学计算机与通信工程学院及河北省海洋感知网络与数据处理重点实验室）
- Shijiazhuang Innovation Research Institute of Northeastern University（东北大学石家庄创新研究院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对现有推荐方法忽视多模态不确定性和静态扁平意图结构的问题，提出UHIFlow框架，通过流匹配量化不确定性并动态构建分层意图，实验证明其显著优于基线。
中文摘要 AI 辅助
对底层用户意图进行建模对于推荐至关重要，但现有方法在处理固有不确定性以及用户兴趣的动态、分层特性方面存在困难。当前方法通常依赖聚类或原型学习来发现一组静态意图。然而，它们面临两个关键挑战：（1）忽略了多模态特征中固有的不确定性；（2）假设意图结构是静态且扁平的，无法适应用户不断变化的决策确定性。为解决这些局限性，我们提出了UHIFlow，一个基于流匹配的不确定性感知分层意图学习框架。首先，我们的跨模态不确定性协同建模（CUSM）模块利用条件流匹配来量化来自视觉和文本模态的不确定性，并对其进行协同对齐。随后，不确定性引导的分层意图生成（UHIG）模块利用这种量化的不确定性动态构建个性化的意图层级，为不确定用户生成粗粒度意图，为偏好明确的用户生成细粒度意图。在三个真实世界数据集上的大量实验表明，UHIFlow显著优于最先进的基线方法。
英文摘要
Modeling the underlying user intent is crucial for recommendation, but existing methods struggle with the inherent uncertainty and the dynamic, hierarchical nature of user interests. Current approaches often rely on clustering or prototype learning to discover a static set of intents. However, they face two critical challenges: (1) they overlook the uncertainty inherent in multimodal features; and (2) they assume a static and flat intent structure, failing to adapt to a user's varying decision certainty. To address these limitations, we propose UHIFlow, an Uncertainty-aware Hierarchical Intent learning framework via Flow matching. First, our Cross-modal Uncertainty Synergistic Modeling (CUSM) module leverages conditional flow matching to quantify uncertainty from visual and textual modalities and synergistically align them. Subsequently, the Uncertainty-guided Hierarchical Intent Generation (UHIG) module uses this quantified uncertainty to dynamically construct a personalized intent hierarchy, generating coarse-grained intents for uncertain users and fine-grained ones for users with clear preferences. Extensive experiments on three real-world datasets demonstrate that UHIFlow significantly outperforms state-of-the-art baselines.
