用锚点避免多模态推荐中的位置坍缩问题
Anchored Alignment: Preventing Positional Collapse in Multimodal Recommender Systems
- 通过轻量投影域的锚点间接对齐多模态特征
- 在4个Amazon数据集上保持推荐精度且提升多模态表达力
- 适合关注多模态结构保留与推荐一致性研究者
多模态推荐系统（MMRS）利用图像、文本和交互信号增强物品表征。然而，近年来基于对齐的MMRS在统一嵌入空间中常模糊模态特有结构并加剧ID主导现象。为此，我们提出AnchorRec框架，在轻量投影域中进行间接锚点对齐。通过解耦对齐与表征学习，AnchorRec在保持各模态原始结构的同时，维持跨模态一致性并避免位置坍缩。在四个Amazon数据集上的实验表明，AnchorRec实现了具有竞争力的Top N推荐准确率；定性分析显示其提升了多模态表达力与一致性。代码已开源：https://github.com/hun9008/AnchorRec。
原文摘要 · Abstract (English)
Multimodal recommender systems (MMRS) leverage images, text, and interaction signals to enrich item representations. However, recent alignment based MMRSs that enforce a unified embedding space often blur modality specific structures and exacerbate ID dominance. Therefore, we propose AnchorRec, a multimodal recommendation framework that performs indirect, anchor based alignment in a lightweight projection domain. By decoupling alignment from representation learning, AnchorRec preserves each modality's native structure while maintaining cross modal consistency and avoiding positional collapse. Experiments on four Amazon datasets show that AnchorRec achieves competitive top N recommendation accuracy, while qualitative analyses demonstrate improved multimodal expressiveness and coherence. The codebase of AnchorRec is available at https://github.com/hun9008/AnchorRec.
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。