返回全部动态
PCGNet：统一共享与特定信息用于时尚搭配推荐
原标题：PCGNet: Unifying Shared and Specific Information for Fashion Matching Recommendations
AI 摘要
该论文提出 PCGNet（个性化兼容图网络），一个多目标图学习框架，用于时尚搭配推荐。它通过对比互信息最大化来提取并对齐共享信息与视图特定模式，统一建模商品兼容性与用户个性化偏好，并引入相关性感知邻居采样和可学习全局图增强以缓解数据稀疏与噪声问题。在两个基准数据集上，PCGNet 在四项评价指标上均显著优于现有方法。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
PCGNet: Unifying Shared and Specific Information for Fashion Matching Recommendations Abstract. With the continuous evolution of e-commerce platforms, enhancing user experience and customer satisfaction are of paramount importance. In the fashion domain, recommending complementary clothing items that match selected pieces is a crucial cross-selling technique that improves customer satisfaction. Nevertheless, fashion matching presents significant challenges, as recommendations must not only align
发布时间：2026-09-15 12:00
抓取时间：2026-09-15 12:18
来源机构：arXiv