基于过渡性超图卷积的捆绑推荐算法研究OA
Transitional hypergraph covolution for bundle recommendation
捆绑推荐是一种在电商平台上广泛应用的推荐策略,其通过向用户推荐个性化的商品组合来实现用户通过单次购买满足多样化的需求.现有基于图卷积网络的推荐模型在捕捉不同实体之间复杂关系以及有效整合来自不同视角的信息上存在局限性.为了解决这些局限性,提出了一种基于过渡性超图卷积的捆绑推荐模型HC4BR.该模型利用过渡性超图卷积捕捉实体之间复杂的高阶关系,通过多粒度层次卷积整合来自不同视角的信息,利用对比学习更好地区分相似实体表示.和目前先进的模型相比,该模型在三个公开数据集上的实验结果分别提升了 3.39%、2.00%和 14.70%,展示了其在解决捆绑推荐复杂挑战方面的有效性以及提升电子商务平台用户体验的潜力.
Bundle recommendation,which aims to suggest personalized groups of items to users,has emerged as an effective strategy in modern e-commerce platforms,allowing users to satisfy diverse needs with a single purchase.Existing models based on graph convolution networks face limitations in capturing the complex relationships between users,items,and bundles as well as effectively integrating information from different interaction views.To address these challenges,HC4BR(Hypergraph Convolution for Bundle Recommendation),a novel transitional hypergraph convolutional model for bundle recommendation is proposed.It employs transitional hypergraph convolution to capture intricate and higher-order relationships among entities,integrates different views based on various user preference strategies during information propagation and incorporates contrastive learning to refine the model ′s ability to distinguish between similar entities,improving its capacity to explore subtle distinctions while reinforcing meaningful connections.Experimental results on three public datasets demonstrate that the model outperforms the state-of-the-art method by 3.39%,2.00%and 14.70%respectively,showcasing its effectiveness in addressing the complex challenges of bundle recommendation and its potential to enhance user experience and business outcomes in e-commerce platforms.
杜鹏翔;冯凯东;李强;厉斌斌;刘文远
燕山大学 人工智能学院(软件学院),河北 秦皇岛 066004燕山大学 人工智能学院(软件学院),河北 秦皇岛 066004河北燕大燕软信息系统有限公司,河北 秦皇岛 066000||燕山大学 河北省网络感知与大数据研究中心,河北 秦皇岛 066004燕山大学 河北省网络感知与大数据研究中心,河北 秦皇岛 066004||燕山大学 经济与管理学院,河北 秦皇岛 066004燕山大学 人工智能学院(软件学院),河北 秦皇岛 066004||燕山大学 河北省网络感知与大数据研究中心,河北 秦皇岛 066004||燕山大学 河北省软件工程重点实验室,河北 秦皇岛 066004
信息技术与安全科学
捆绑推荐图卷积网络超图学习对比学习
bundle recommendationgraph convolutional networkhypergraph learningcontrastive learning
《燕山大学学报》 2026 (5)
449-460,12
河北省自然科学基金资助项目(F2023203058,F2022203045)河北省软件工程重点实验室资助项目(2256763H)河北省科学技术研究与发展计划-重点研发计划资助项目(22310301D)秦皇岛市科学技术研究与发展计划资助项目(202401A004)
评论