通过相似性传播降低多模态推荐中的不确定性
Propagating Similarity, Mitigating Uncertainty: Similarity Propagation-enhanced Uncertainty for Multimodal Recommendation
- 构建内容与行为相似图，动态优化多模态表示
- 自适应融合特征，对可靠模态赋予更高权重
- 适合处理含噪图像/模糊文本的推荐场景
多模态推荐系统在现代平台中至关重要，但常受模态特征固有噪声和不确定性的困扰，如模糊图像、多样视觉表现或模糊文本。现有方法往往忽略模态特异性不确定性，导致特征融合效果不佳，且未能利用用户与物品间的丰富相似性模式来优化表示及其不确定性估计。为此，我们提出新框架SPUMR，通过构建模态相似图与协同相似图，从内容与行为双视角优化表示，并引入不确定性感知偏好聚合模块，自适应融合多模态特征，提升可靠模态权重。在三个基准数据集上的大量实验表明，SPUMR显著优于现有领先方法。
原文摘要 · Abstract (English)
Multimodal Recommendation (MMR) systems are crucial for modern platforms but are often hampered by inherent noise and uncertainty in modal features, such as blurry images, diverse visual appearances, or ambiguous text. Existing methods often overlook this modality-specific uncertainty, leading to ineffective feature fusion. Furthermore, they fail to leverage rich similarity patterns among users and items to refine representations and their corresponding uncertainty estimates. To address these challenges, we propose a novel framework, Similarity Propagation-enhanced Uncertainty for Multimodal Recommendation (SPUMR). SPUMR explicitly models and mitigates uncertainty by first constructing the Modality Similarity Graph and the Collaborative Similarity Graph to refine representations from both content and behavioral perspectives. The Uncertainty-aware Preference Aggregation module then adaptively fuses the refined multimodal features, assigning greater weight to more reliable modalities. Extensive experiments on three benchmark datasets demonstrate that SPUMR achieves significant improvements over existing leading methods.
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。