计算机工程与科学2024，Vol.46Issue(4)：707-715,9.DOI:10.3969/j.issn.1007-130X.2024.04.015
双视图对比学习引导的多行为推荐方法
A dual-view contrastive learning-guided multi-behavior recommendation method
摘要
Abstract
Multi-behavior recommendation(MBR)typically utilizes various types of user interaction behaviors(such as browsing,adding to cart,and purchasing)to learn user preferences for the target be-havior(i.e.,purchasing).Due to the impact of sparse supervision signals,existing MBR models often suffer from poor recommendation performance.Recently,contrastive learning has achieved success in mining auxiliary supervision signals from raw data itself.Inspired by this,we propose a dual-view con-trastive learning-guided method to enhance MBR.Firstly,we construct two views that can capture both local and high-order structural information using multi-behavior interaction data.Then,we design two different view encoders to learn user and item embeddings on these complementary views.Finally,we use cross-view collaborative contrastive learning to mutually supervise and learn better embeddings.Ex-perimental results on two real-world datasets demonstrate that our proposed method significantly out-performs baseline methods.关键词
协同过滤/对比学习/图神经网络/多行为推荐Key words
collaborative filtering/contrastive learning/graph neural network/multi-behavior recom-mendation分类
信息技术与安全科学引用本文复制引用
李清风,金柳,马慧芳,张若一..双视图对比学习引导的多行为推荐方法[J].计算机工程与科学,2024,46(4):707-715,9.基金项目
国家自然科学基金(62167007,61762078,61363058) （62167007,61762078,61363058）
西北师范大学青年教师能力提升计划(NWNULKQN2019-2) （NWNULKQN2019-2）
