推荐系统-召回部分-样本构建

这是对之前知识的补漏：必须要拿适当的曝光未点击最为hard负样本，线上才能得到较好的效果。理论依据如下：

DeepLearning搜索与推荐

相关

文献阅读Understanding and improving deep learning-based rolling bearing fault di

PointNet：Deep Learning on Point Sets for 3D Classification and Segmentation

论文翻译：2018_Deep Learning for Acoustic Echo Cancellation in Noisy and Double-Ta

Embedding技术在商业搜索与推荐场景的实践

Deep Learning论文笔记之（二）Sparse Filtering稀疏滤波

论文阅读 TEMPORAL GRAPH NETWORKS FOR DEEP LEARNING ON DYNAMIC GRAPHS

标签