- 【论文阅读】User Profiling based Deep
- 【阅读笔记】A Deep Learning-Based Syst
- 【5分钟 Paper】Reinforcement Learnin
- 推荐系统论文阅读(二十)-阿里妈妈基于用户长序列历史行为的推荐S
- Over-the-Air Deep Learning Based
- [Sche/DLsys]Scheduling CPU for G
- 论文-Switch-based Active Deep Dyna
- 推荐系统遇上深度学习(八十七)-[阿里]基于搜索的用户终身行为序
- DEEP GRAPH INFOMAX 阅读笔记
- 《Over the Air Deep Learning Base
Terminology
word2vec:

doc2vec embedding:

User profile
R: 浏览过的文章数量
rh:doc2vec embedding
U:user profile(用户概况)which accounts for both the short term as well as the long term interests of the users.
采用了三种形式来表示user profile以便理解时间上的模式。加了discount的模型是为了给最近阅读的文章更大权重,以前的权重更小。



DSSM模型(Deep Structured Semantic Model)

看做高斯分布不再合适,还要考虑潜在data和排序,改进loss函数为


实验
1. Settings
数据集:CLEF NewsREEL 2017. 用gensim 来学习doc2vec embedding(size设为300)。数据集中77%为小于3篇,用10-15篇阅读量的user来train(for cold start problem),2-4篇的来test。>15篇的user在frequency(?)上变化比较大,所以不采用。
leave-one-out法来做evaluation,performance用HR@k(测试item是否在)top k list中;NDCG accounts for the position of the hit by assigning higher scores to hits at top ranks.
(矩阵分解)Baseline:BPR ,eALS ,NeuMF 等方法(待查)
用Keras 做,training集合和validation集合比例为4:1。全连接层的权重初始化用范围内均匀分布。batch size为256,梯度用adabelta。

2. Performance



网友评论