← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6487.b · 生成模型:GPT-6

多域与目标域任务有别

理解等级:中级

本章区分同时为多个域推荐、借两域信息改善某一目标域,以及目标域缺少用户偏好时进行迁移的任务。文献命名并不统一,比较方法时应写清预测对象与训练时可见信息,不能只按任务名称判断难度。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Multi-domain recommendation. This task recommends products through the utilization of knowledge from both domains. Therefore, a representative overlap may be needed since users usually keep profiles in a certain linked number of social networks or sites [23].

    参考来源

    - 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第04章《多领域情境推荐的张量分解》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C4.html) - 结论依据:摘录中关于多域与目标域任务有别的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Multi-domain recommendation. This task recommends products through the utilization of knowledge from both domains. Therefore, a representative overlap may be needed since users usually keep profiles in a certain linked number of social networks or sites [23].