通过上图理解本文提出的1-hop和2-hop，考虑这两种关系的时候，是基于target user 和 target item这样的成对样本的。（注意本文中的G(u|v)的定义容易让人产生误解，这里的u其实是一个集合。Eq 10 中的G(u)和G(u|v)中的u不是一个东西，前者是target user，后者是集合示意； 另外S=|G(u)|=G(u|v)是人为设置的）
当考虑target user-item时，其实一个考虑的是1-hop，另一个是2-hop（如上图上半部分：user是1-hop；而item是2-hop），当通过对列向量进行sum poolling时，就会得到1-hop中的每个item同2-hop整体之间的联系强弱（weight）。通过这个weights进一步aggregate 1-hop中item的表达
通过这样的形式，会为每一个t构建一个user和item的表达。把所有的user/item的表达进行attention加权聚合，就得到了最后的user/item表达。
这里有几个实验设计可以借鉴下或引用下：
（1）15天为一个delat t（the span of one timestep）
（2）当某个t没有用户行为是，设置一个统一的表达
（3）把所有的timesteps的表达通过一个attention 加权聚合
（4）把baselines进行分组，描述结果的时候就可以分组描述了
另外，本文代码开源：TensorFlow上实现的
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Sequential Recommendation with Dual Side Neighbor-based Collaborative Relation Modeling | |||||||||||
| 文献作者 | Jiarui Qin; Kan Ren | ||||||||||
| 文献发表年限 | 2019 | ||||||||||
| 文献关键字 | |||||||||||
| Sequential Recommendation, Collaborative Filtering, Co-Attention; GRU | |||||||||||
| 摘要描述 | |||||||||||
| Sequential recommendation task aims to predict user preference over items in the future given user historical behaviors. The order of user behaviors implies that there are resourceful sequential patterns embedded in the behavior history which reveal the underlying dynamics of user interests. Various sequential recommendation methods are proposed to model the dynamic user behaviors. However, most of the models only consider the user’s own behaviors and dynamics, while ignoring the collaborative relations among users and items, i.e., similar tastes of users or analogous properties of items. Without modeling collaborative relations, those methods suffer from the lack of recommendation diversity and thus may have worse performance. Worse still, most existing methods only consider the user-side sequence and ignore the temporal dynamics on the item side. To tackle the problems of the current sequential recommendation models, we propose Sequential Collaborative Recommender (SCoRe) which effectively mines high-order collaborative information using cross-neighbor relation modeling and, additionally utilizes both user-side and item-side historical sequences to better capture user and item dynamics. Experiments on three real-world yet large-scale datasets demonstrate the superiority of the proposed model over strong baselines. | |||||||||||
