Scholarlink

<p>Multimodal recommender systems improve recommendation accuracy by incorporating item multimodal features (e.g., text, images) alongside user-item interactions. However, they face two critical challenges: (1) local user interests in multimodal features are often obscured by irrelevant content (e.g., background clutter in product images), and (2) behavioral data contains pervasive low-credibility interactions (e.g., accidental clicks) that propagate noise through graph-based recommenders. Notably, over-reliance on region-of-interest (ROI) features during graph construction may introduce spurious edges by ignoring global contextual relationships, exacerbating semantic distortion. To address these issues, we propose CLID (Cross-modal Local Interest Denoising), a novel framework integrating <b>C</b>ross-Modal <b>L</b>ocal <b>I</b>nterest Contrast and Dual-Graph <b>D</b>enoising. First, our local interest contrast mechanism employs bidirectional text-visual guided attention alignment and a contrastive loss function to enhance discriminative local features—for instance, it learns to jointly focus on the visual and textual characteristics of "sleeve design" in garment products while suppressing irrelevant background features and redundant textual features. Crucially, it adaptively weights local features against global representations to prevent ROI-induced bias. Second, the dual-graph denoising architecture combines: (i) a local graph that stabilizes neighbor aggregation via structural consistency to attenuate noisy interactions and (ii) a hypergraph capturing group-wise behavioral patterns, where high-confidence interactions are reinforced through co-occurrence frequency weighting. Experiments demonstrate that CLID significantly improves recommendation performance on three Amazon review datasets: Baby; Clothing, Shoes and Jewelry; as well as Sports and Outdoors. The proposed CLID framework provides a generalizable contrast-and-denoise paradigm for robust multimodal recommendation, effectively bridging fine-grained feature enhancement with noise-resilient graph learning.The code implementation is openly available at the following repository: <a href="https://github.com/Qiyx5025/CLID-master">https://github.com/Qiyx5025/CLID-master</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Cross-modal local interest contrast with Dual-graph denoising for multimodal recommendation

  • 期刊论文

  • 发表日期：

    2026年1月16日

查看全文
  • Yuxin Qi,
  • Quangui Zhang,
  • Xinqiang Ma,
  • Xie Feng,
  • Qiang Li,
  • Yi Huang

摘要

Multimodal recommender systems improve recommendation accuracy by incorporating item multimodal features (e.g., text, images) alongside user-item interactions. However, they face two critical challenges: (1) local user interests in multimodal features are often obscured by irrelevant content (e.g., background clutter in product images), and (2) behavioral data contains pervasive low-credibility interactions (e.g., accidental clicks) that propagate noise through graph-based recommenders. Notably, over-reliance on region-of-interest (ROI) features during graph construction may introduce spurious edges by ignoring global contextual relationships, exacerbating semantic distortion. To address these issues, we propose CLID (Cross-modal Local Interest Denoising), a novel framework integrating Cross-Modal Local Interest Contrast and Dual-Graph Denoising. First, our local interest contrast mechanism employs bidirectional text-visual guided attention alignment and a contrastive loss function to enhance discriminative local features—for instance, it learns to jointly focus on the visual and textual characteristics of "sleeve design" in garment products while suppressing irrelevant background features and redundant textual features. Crucially, it adaptively weights local features against global representations to prevent ROI-induced bias. Second, the dual-graph denoising architecture combines: (i) a local graph that stabilizes neighbor aggregation via structural consistency to attenuate noisy interactions and (ii) a hypergraph capturing group-wise behavioral patterns, where high-confidence interactions are reinforced through co-occurrence frequency weighting. Experiments demonstrate that CLID significantly improves recommendation performance on three Amazon review datasets: Baby; Clothing, Shoes and Jewelry; as well as Sports and Outdoors. The proposed CLID framework provides a generalizable contrast-and-denoise paradigm for robust multimodal recommendation, effectively bridging fine-grained feature enhancement with noise-resilient graph learning.The code implementation is openly available at the following repository: https://github.com/Qiyx5025/CLID-master.