期刊文献+

基于动态卷积和自注意力的序列推荐模型

Sequence Recommendation Model Based on Dynamic Convolution and Self-attention
下载PDF
导出
摘要 序列推荐是根据用户和项目的历史交互记录对用户兴趣建模,进行下一项目推荐。序列对用户兴趣建模通常分为长期兴趣依赖和短期兴趣依赖。现有的方法或按交互顺序先后将序列分割,分别对长短期兴趣依赖建模,割裂地对用户兴趣建模;或以不同的特征提取技术并行提取同一段交互序列的特征,获得全局和局部的兴趣表示,忽略不同时刻的用户意图存在该时刻行为上下文中这一事实。本文提出一种利用动态卷积和自注意力构建动态兴趣的序列推荐模型DConvSA。使用动态卷积提取局部动态兴趣,根据不同上下文项目生成卷积核,自适应计算项目的重要性。结合自注意力机制,获得全局显著项目依赖。以显式的方式融合每个时刻的全局和局部兴趣依赖,从而更好地对不同时刻兴趣间的联系建模。在3个公开数据集上进行实验,结果表明,其召回率、平均倒数排名和归一化折损累计增益在MovieLens-1M数据集上至少提升1.53%、3.77%和3.28%,在Amazon Beauty数据集上至少提升1.86%、1.94%和2.46%,在Steam数据集上至少提升0.22%、0.97%和1.08%。 Sequence recommendation dynamically models user interests according to the historical interaction records of users and items,and recommends next item.The sequence modeling user interests is usually divided into long-term interest depen-dency and short-term interest dependency.The existing methods either divide the sequence according to the interaction order,re-spectively model the long-term and short-term interest dependence,separately model the user interest,or extract the features of the same interactive sequence in parallel with different feature extraction technologies to obtain the global and local interest repre-sentation,ignoring the fact that the user intention at different times exists in the behavior context at that time.This paper pro-poses DConvSA to model dynamic interest by using dynamic convolution and self-attention.Dynamic convolution is used to ex-tract local dynamic interest,and convolution kernel is generated according to different context items to adaptively calculate the importance of items.Combined with the self-attention mechanism,the overall significant item dependency is obtained.At the same time,the global and local interest dependencies at each time are fused in an explicit way to better model the relationship between interests at different times.Experiments are conducted on three public datasets,using recall rate,average reciprocal ranking and normalized cumulative gain for performance evaluation.The results show that the recall rate,mean reciprocal rank-ing and normalized discounted cumulative gain increased by at least of 1.53%,3.77%and 3.28%on the MovieLens-1M dataset,1.86%,1.94%and 2.46%on the Amazon Beauty dataset,and 0.22%,0.97%and 1.08%on the Steam dataset.
作者 郑海利 陈平华 ZHENG Hai-li;CHEN Ping-hua(School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China)
出处 《计算机与现代化》 2023年第10期9-16,共8页 Computer and Modernization
基金 广东省重点领域研发计划项目(2020B0101100001)。
关键词 序列推荐 动态卷积 自注意力 局部兴趣 全局兴趣 sequence recommendation dynamic convolution self-attention local interest global interest
  • 相关文献

参考文献2

二级参考文献4

共引文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部