摘要
已有基于会话的推荐系统大多根据最后一个点击的项目与当前会话的用户偏好的相关性进行推荐,忽略了在其他会话中可能包含了与当前会话相关的项目转换,这些项目转换可能对用户的当前偏好也有一定的影响,因此需要从局部会话和整体会话的角度来综合分析用户偏好;并且这些推荐系统大多忽略了位置信息的重要性,而与预测位置越近的项目可能与当前用户兴趣的相关性越高。针对这些问题,提出一种基于全局增强的图神经网络的推荐模型(GEL-GNN)。GEL-GNN旨在根据所有会话预测用户的行为,它使用GNN来捕获当前会话的全局和局部之间的关系,使用LSTM来捕获全局层面会话间的关系。首先,通过注意力机制层将用户的偏好表示为基于全局层面和局部层面会话兴趣的组合;然后,使用反向位置信息衡量当前位置和预测位置之间的距离,以便更加准确地预测用户行为。在3个真实的数据集上进行了大量的实验,实验结果表明GEL-GNN优于现有的基于会话的图神经网络推荐模型。
Most of the existing session based recommendation systems recommend based on the correlation between the last clicked item and the user preference of the current session, and ignore that there may be item transitions related to the current session in other sessions, while these item transitions may also have a certain impact on users’ current preferences Hence, it is indispensable to analyze users’ preferences comprehensively from the perspective of local session and global session.Furthermore, most of these recommendation systems ignore the importance of location information, whereas items closer to the predicted location may be more relevant to the current user’s interests.To solve these problems, this paper proposes a recommendation model based on global enhanced graph neural network with LSTM(GEL-GNN).GEL-GNN aims to predict the behavior of users according to all sessions, and GNN is employed to capture the global and local relationship of the current session, while LSTM is employed to capture the relationship between sessions at the global level.Firstly, users’ preferences are to be translated as a combination of conversation interests based on global and local levels through the attention mechanism layer.Then, the distance between the current position and the predicted position is measured with the reverse position information, so that user behavior can be predicted more accurately.A number of experiments are conducted on three real data sets.Experimental results show that GEL-GNN is superior to the existing session-based graph neural network recommendation models.
作者
周芳泉
成卫青
ZHOU Fang-quan;CHENG Wei-qing(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China)
出处
《计算机科学》
CSCD
北大核心
2022年第9期55-63,共9页
Computer Science
基金
国家自然科学基金(61170322)
江苏省研究生教育教学改革课题(JGZZ19_038)。
关键词
基于会话的推荐
图神经网络
注意力机制
位置信息
Session-based recommendations
Graph neural network
Attention mechanism
Position information
