本文的主要贡献，是利用session色当中item sequences构建成个item graph（刻画了item 之间complex transitions），再基于GNN为每一个顶点（item）学出一个表达。
基于以上的item representation，再利用attention model which guided by last item representation，学出一个session' global representation，同时把last item representation当作 session' local representation. global + local (concatenation: session' hybird representation).
最后根据 session' hybird representation和item representation做出推荐。
注意，这里值得学习的是：怎么把已知的两两关系（graph structure）融合到神经网络当中，如Eq.(1):即乘以这个已知的关系矩阵，类似一个权重矩阵。
这里的GNN，其实有多层，每一层都学出了item representations，在学习某个item representation的时候，所有与它有关系的item都通过上述的关系矩阵发生联系。知道学习和借鉴。
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Session-based Recommendation with Graph Neural Networks | |||||||||||
| 文献作者 | Shu Wu; | ||||||||||
| 文献发表年限 | 2019 | ||||||||||
| 文献关键字 | |||||||||||
| 融合一个关系已知的矩阵；Graph Neural Networks (GNN); attention model; long- and short-term; session-based; Yoochoose; Diginetica | |||||||||||
| 摘要描述 | |||||||||||
| The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. Though achieved promising results, they are insufficient to obtain accurate user vectors in sessions and neglect complex transitions of items. To obtain accurate item embed- ding and take complex transitions of items into account, we propose a novel method, i.e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity. In the proposed method, session sequences are modeled as graph-structured data. Based on the session graph, GNN can capture complex transitions of items, which are difficult to be revealed by previous conventional sequential methods. Each session is then represented as the composition of the global preference and the current interest of that session using an attention network. Extensive experiments conducted on two real datasets show that SR-GNN evidently outperforms the state-of-the-art session-based recommendation methods consistently. | |||||||||||
