华南理工大学学报（自然科学版）2025，Vol.53Issue(9)：11-21,11.DOI:10.12141/j.issn.1000-565X.240088
基于多兴趣对比的深度强化学习推荐模型
Deep Reinforcement Learning Recommendation Model Based on Multi-Interest Contrast
摘要
Abstract
Deep Reinforcement Learning(DRL)is widely applied in recommender systems to dynamically model user interests and maximize cumulative user benefits.However,the sparsity of user feedback has become a signifi-cant challenge for DRL-based recommendation algorithms.Contrastive learning,as a self-supervised learning method,enhances user interest representation by constructing multiple perspectives,thereby alleviating the issue of sparse user feedback.Existing contrastive learning methods typically rely on heuristic-based augmentation strate-gies,which often lead to the loss of key information and fail to fully utilize heterogeneous interaction data.To address these issues,this paper proposed a multi-interest oriented contrastive deep reinforcement learning recom-mendation(MOCIR)model.The model consists of two key modules:a contrastive representation module and a policy network module.The contrastive representation module utilizes a Heterogeneous Information Network(HIN)to model the user's local interests from different aspects while capturing their global interests based on raw interac-tion data.It then treats the global and local interests of the same user as positive pairs and those of different users as negative pairs for contrastive learning,effectively enhancing user interest representation.The policy network module aggregates user state representations and generates recommendations.The two modules are trained using an alternating update mechanism.Experimental results on three benchmark datasets show that the proposed model out-performs several DRL-based models in recommendation performance,effectively addressing the problem of sparse user feedback in recommendations.关键词
多兴趣/强化学习/对比学习/异质信息网络Key words
multi-interest/reinforcement learning/contrastive learning/heterogeneous information network分类
信息技术与安全科学引用本文复制引用
刘慧婷,刘绍雄,王佳乐,赵鹏..基于多兴趣对比的深度强化学习推荐模型[J].华南理工大学学报（自然科学版）,2025,53(9):11-21,11.基金项目
国家自然科学基金项目(62576003) （62576003）
安徽省高校协同创新项目(GXXT-2022-040) （GXXT-2022-040）
安徽省自然科学基金项目(2008085MF219,2108085MF212) （2008085MF219,2108085MF212）
安徽省高校自然科学研究项目(KJ2021-A0040,KJ2021-A0043)Supported by the National Natural Science Foundation of China(62576003),the University Synergy Innovation Program of Anhui Province(GXXT-2022-040),the Natural Science Foundation of Anhui Province(2008085MF219,2108085MF212)and the Provincial Natural Science Foundation of Anhui Higher Education Institution of China(KJ2021-A0040,KJ2021-A0043) （KJ2021-A0040,KJ2021-A0043）
