知识卡片
跨域稳健性要改变连接强度
跨域方法可能随用户重叠比例、目标域数据密度与目标用户画像长度而变化。敏感性分析在控制条件下改变这些因素,才能看出方法依赖哪种信息。只在完全重叠条件得分高,不证明弱连接情形仍有效。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
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
Cross-domain recommender systems performance can be impacted by some parameters such as [7]: (i) the source and target domains' overlap level [86], (ii) the target domain's data density [18], and (iii) the target user's profile size [29]. Therefore, a sensitivity analysis of these three parameters is important for cross-domain algorithms.
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:摘录中关于跨域稳健性要改变连接强度的定义、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:Cross-domain recommender systems performance can be impacted by some parameters such as [7]: (i) the source and target domains' overlap level [86], (ii) the target domain's data density [18], and (iii) the target user's profile size [29]. Therefore, a sensitivity analysis of these three parameters is important for cross-domain algorithms.