Journal of Frontiers of Computer Science and Technology ›› 2024, Vol. 18 ›› Issue (3): 768-779.DOI: 10.3778/j.issn.1673-9418.2211090

• Artificial Intelligence·Pattern Recognition • Previous Articles     Next Articles

Session Recommendation Algorithm Combining Item Transition Relations and Time-Order Information

WU Wenzheng, LU Xianling   

  1. School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China
  • Online:2024-03-01 Published:2024-03-01

融合物品转换关系和时序信息的会话推荐算法

吴文政,卢先领   

  1. 江南大学 物联网工程学院,江苏 无锡 214122

Abstract: Aiming at the problem that the existing graph neural network session recommendation algorithm ignores all kinds of auxiliary information, which leads to the inability to accurately model the session sequence, a session recommendation algorithm combining the item transition relations and time-order information (RTSR) is proposed. Firstly, the shortest path sequence between any two nodes is obtained by using the graph network structure, which is encoded as the item transition relations between corresponding items through the gated recurrent unit (GRU), and then the global dependency information of the session is captured from the perspective of the graph by combining the self-attention mechanism. At the same time, a lossless graph coding scheme is designed to alleviate the problem of information loss in the process of session graph coding. The scheme quantifies the time-order information in the session sequence reasonably, and takes it as the weight of the edges in the session graph, and then combines the gated graph sequence neural network to obtain the local dependency information of the session. Finally, with linear combination of global dependency information and local dependency information, and in combination with reverse position information,  the user??s preference for item is finally generated, and the recommendation list is given. The performance comparison experiment with mainstream models such as SR-GNN, GC-SAN and GCE-GNN on the public benchmark datasets Gowalla and Diginetica shows that RTSR  improves at least 6.13% and 1.58% in average reciprocal ranking respectively, and the recommendation accuracy is also improved accordingly.

Key words: graph neural network, session recommendation, shortest path sequence, time-order information, reverse position information

摘要: 针对现有图神经网络会话推荐算法忽略了各类辅助信息,导致不能准确地建模会话序列的问题,提出了一种融合物品的转换关系和时序信息的会话推荐算法(RTSR)。首先利用图网络结构得到任意两个节点之间的最短路径序列,经过双向门控循环单元(GRU)将其编码为对应物品之间的转换关系,再结合自注意力机制从图的角度捕捉会话的全局依赖信息。同时设计了一种无损图编码方案来缓解会话图编码过程中信息损失的问题。该方案将会话序列中的时序信息进行合理的量化,并将其作为会话图中边的权重,再结合门控图神经网络获取会话的局部依赖信息。最后,线性组合全局依赖信息和局部依赖信息并结合反向位置信息,最终生成用户对物品的兴趣偏好,并给出推荐列表。在公共基准数据集Gowalla和Diginetica上与SR-GNN、GC-SAN、GCE-GNN等主流模型进行性能对比实验,结果表明RTSR在平均倒数排名方面分别至少提高了6.13%和1.58%,同时推荐精准度方面也有相应的提高。

关键词: 图神经网络, 会话推荐, 最短路径序列, 时序信息, 反向位置信息