当前位置: X-MOL 学术ACM Trans. Inf. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Exploiting Cross-session Information for Session-based Recommendation with Graph Neural Networks
ACM Transactions on Information Systems ( IF 5.4 ) Pub Date : 2020-05-25 , DOI: 10.1145/3382764
Ruihong Qiu 1 , Zi Huang 1 , Jingjing Li 2 , Hongzhi Yin 1
Affiliation  

Different from the traditional recommender system, the session-based recommender system introduces the concept of the session , i.e., a sequence of interactions between a user and multiple items within a period, to preserve the user’s recent interest. The existing work on the session-based recommender system mainly relies on mining sequential patterns within individual sessions, which are not expressive enough to capture more complicated dependency relationships among items. In addition, it does not consider the cross-session information due to the anonymity of the session data, where the linkage between different sessions is prevented. In this article, we solve these problems with the graph neural networks technique. First, each session is represented as a graph rather than a linear sequence structure, based on which a novel F ull G raph N eural N etwork (FGNN) is proposed to learn complicated item dependency. To exploit and incorporate cross-session information in the individual session’s representation learning, we further construct a B roadly C onnected S ession (BCS) graph to link different sessions and a novel Mask-Readout function to improve session embedding based on the BCS graph. Extensive experiments have been conducted on two e-commerce benchmark datasets, i.e., Yoochoose and Diginetica , and the experimental results demonstrate the superiority of our proposal through comparisons with state-of-the-art session-based recommender models.

中文翻译:

使用图神经网络利用跨会话信息进行基于会话的推荐

不同于传统的推荐系统,基于会话的推荐系统引入了会议,即在一段时间内用户与多个项目之间的一系列交互,以保留用户最近的兴趣。基于会话的推荐系统的现有工作主要依赖于挖掘单个会话中的顺序模式,这些模式的表达能力不足以捕捉项目之间更复杂的依赖关系。另外,由于会话数据的匿名性,不考虑跨会话信息,防止了不同会话之间的联系。在本文中,我们使用图神经网络技术解决了这些问题。首先,每个会话都表示为一个图而不是一个线性序列结构,基于它的小说F乌尔G拉夫ñ欧元ñ网络(FGNN)被提出来学习复杂的项目依赖。为了在单个会话的表示学习中利用和合并跨会话信息,我们进一步构建了一个路漫漫其修远兮C连接的小号会话(BCS)图链接不同的会话和一个新颖的掩码读出功能,以改进基于 BCS 图的会话嵌入。已经在两个电子商务基准数据集上进行了广泛的实验,即优选择Diginetica,实验结果通过与最先进的基于会话的推荐模型进行比较,证明了我们提议的优越性。
更新日期:2020-05-25
down
wechat
bug