基于轻量级图卷积和隐式反馈增强的多样化推荐  

Diversified Recommendation Based on Light Graph Convolution Networks and Implicit Feedback Enhancement

作　　者：黄春淦 王桂平 吴波 白鑫 HUANG Chungan;WANG Guiping;WU Bo;BAI Xin(School of Information Science and Engineering,Chongqing Jiaotong University,Chongqing 400074,China)

机构地区：[1]重庆交通大学信息科学与工程学院,重庆400074

出　　处：《计算机科学》2024年第S01期669-679,共11页Computer Science

基　　金：国家自然科学基金(62073051);重庆交通大学研究生教育创新基金(2020S0054)。

摘　　要：近年来,研究人员一直在努力提高推荐系统的准确性,而忽视了多样化对用户满意度的重要影响。目前大多数多样化推荐算法在传统算法生成的准确性候选列表后施加多样性约束进行后处理。然而,这种解耦设计总是导致推荐系统的次优状态。与此同时,尽管利用图卷积神经(Graph Convolution Networks,GCN)的推荐算法在提高推荐准确性方面的有效性已得到证实,但用于推荐的适用性和多样性设计仍然被忽视。此外,推荐算法采用用户购买这一单一的显式反馈无可避免地陷入“推荐过剩”。因此,提出一种端到端的多样化轻量级图卷积网络推荐模型(Diversified Light Graph Convolution Networks Recommendation,DLGCRec)来克服以上弊端。首先,将图卷积简化为轻量级图卷积(Light Graph Convolution Networks,LGCN)以便于推荐,并利用轻量级图卷积将多样化推向上游准确性匹配推荐过程。然后,在轻量级图卷积的采样阶段,利用引入了用户隐式反馈的多样性增强负采样来探索用户的多样化偏好。最后,利用多层特征融合策略捕获节点的完整特征嵌入,提升推荐性能。在真实数据集上进行实验,结果验证了DLGCRec在适用推荐和提升多样性方面的有效性。进一步的消融研究证实,DLGCRec有效地缓解了准确性-多样性困境。In recent years,researchers have been striving to improve the accuracy of recommendation systems while ignoring the critical impact of diversity on user satisfaction.Most current diversified recommendation algorithms impose diversity constraints after the accuracy candidate list generated by traditional post-processing algorithms.However,this decoupled design consistently results in a sub-optimal system.Meanwhile,although the effectiveness of recommendation algorithms using graph convolution networks(GCN)in improving recommendation accuracy has been demonstrated,the applicability and diversity design for recommendation remain neglected.In addition,recommendation algorithms employing a single explicit user feedback of purchasing inevitably fall into“recommendation overload”.Therefore,an end-to-end diversified light graph convolution networks recommendation(DLGCRec)is proposed to overcome these drawbacks.Firstly,GCN is simplified to light graph convolution networks(LGCN)to be suitable for recommendation,and LGCN is utilized to push diversity upstream to the recommendation process of accuracy match.Then,in the sampling phase of LGCN,diversity-boosted negative sampling that introduces user implicit feedback is utilized to explore the user’s diversified preferences.Finally,a multi-layer feature fusion strategy is utilized to capture the complete feature embedding of the nodes to enhance the recommendation performance.Experimental results on real datasets validate the effectiveness of DLGCRec in applying in recommendations and enhancing diversity.Further ablation studies confirm that DLGCRec effectively mitigates the accuracy-diversity dilemma.

关 键 词：推荐系统 多样性 图卷积 隐式反馈 准确性-多样性困境 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]