融合自注意力机制与长短期偏好的序列推荐模型

Sequential recommendation model that combines self-attention mechanism with long-term and short-term preferences

针对现有的序列推荐算法仅利用短期顺序行为进行推荐,而没有充分考虑用户的长期偏好和项目之间更深层次的联系等问题,提出一种融合自注意力机制与长短期偏好的序列推荐模型(combines self-attention with long-term and short-term recommendation,CSALSR)。该模型首先建模用户和项目的潜在特征表示,将用户短期交互序列中的项目成对编码为三向张量,然后经过自注意力机制模块并使用卷积神经网络(convolutional neural network,CNN)从用户的顺序模式中提取项目间更深层次的联系。同时考虑用户的长期偏好,将相似用户的嵌入作为补充增强用户表征。在MovieLens-1M和Gowalla数据集上,实验结果表明提出的方法在准确率precision@N、召回率recall@N、均值平均精度(mean average precision,MAP)上优于其他方法。

In order to solve the problem that the existing sequence recommendation algorithms only use short-term sequential behaviors to make recommendations,but fail to fully consider the long-term preference of users and the deeper relationship between items,this paper proposed a sequential recommendation algorithm CSALSR that it integrated self-attention mechanism and long-term and short-term preference.This model embedded the user and the item into the vector respectively,and regarded the pairwise encoding of the item in short-term interaction sequence as a three-way tensor.Then,it added self-attention mechanism on the three-way tensor and used convolutional neural network to extract the deeper connection between items from the order pattern of users.At the same time,considering the long-term preference of users,it took the embedding of similar users as a supplement to enhance the user representation.Experimental results show that the proposed method on MovieLens-1M and Gowalla data sets is superior to other methods in precision@N,recall@N and MAP.