基于自监督图卷积和注意力机制实现隐式反馈降噪的社交推荐  

Denoising Implicit Feedback with Self-Supervised Graph Convolution Network and Attention Mechanism for Social Recommendation

作　　者：郭向星 周魏[1,2] 杨正益 文俊浩[1,2] 杨佳佳[1] 刘蔓 GUO Xiang-xing;ZHOU Wei;YANG Zheng-yi;WEN Jun-hao;YANG Jia-jia;LIU Man(School of Big Data&Software Engineering,Chongqing University,Chongqing 400044,China;Key Laboratory of Dependable Service Computing in Cyber Physical Society(Chongqing University),Ministry of Education,Chongqing 400044,China;China Mobile Group Chongqing Co.,Ltd.,Chongqing 401320,China)

机构地区：[1]重庆大学大数据与软件学院,重庆400044 [2]信息物理社会可信服务计算教育部重点实验室(重庆大学),重庆400044 [3]中国移动通信集团重庆有限公司,重庆401320

出　　处：《电子学报》2025年第1期151-162,共12页Acta Electronica Sinica

基　　金：重庆市技术创新与应用发展重大项目(No.CSTB2022TIAD-STX0006);国家自然科学基金(No.72074036,No.62072060)。

摘　　要：基于图神经网络的社交推荐系统取得了较好的性能,然而,基于图神经网络的社交推荐模型存在以下挑战:基于图神经网络的模型的邻域聚集操作会放大用户的隐式行为中的噪声,使得用户和物品的向量表示存在偏差;用户物品图中的边和用户社交关系图中的边的异质性,导致基于图神经网络在两张图上学习到的用户向量表示存在于不同的语义空间,直接融合往往得到次优的向量表示.针对上述问题,本文提出了基于自监督图卷积和注意力机制实现隐式反馈降噪的社交推荐模型.该模型从原始的用户物品图中捕捉用户的真实兴趣,生成降噪的用户物品交互图;提出一种新颖的用户向量融合方法,对异质的用户向量表示进行融合.在两个公开数据集上的实验结果表明,所提出的模型在不同数据集上的推荐性能均较基线模型有显著提升.在lastfm数据集上,推荐性能提升了1.18%至3.87%;在ciao数据集上,推荐性能提升了3.56%至7.31%.通过消融实验验证了模型各个模块的有效性.Social recommender systems based on graph neural networks(GNNs)have achieved promising performance.However,challenges exist in GNN-based social recommendation models,such as the neighborhood aggregation operation of GNN-based models amplifying noise in users'implicit behaviors,resulting in suboptimal user and item representations.Additionally,the heterogeneity of edges in the user-item graph and the user social relationship graph leads to user representations learned on two different semantic spaces,where direct fusion also results in suboptimal representations.To address these issues,this paper proposes a social recommendation model based on self-supervised graph convolution and an attention mechanism to achieve implicit feedback noise reduction.The model captures users'true interests from the original user-item graph,generating a denoised user-item interaction graph;a novel method is introduced for fusing user vectors to integrate heterogeneous user vector representations.Experimental results on two public datasets demonstrate that the proposed model significantly improves the recommendation performance over the baseline models.Specifically,on the lastfm dataset,the performance improvement ranges from 1.18%to 3.87%,while on the ciao dataset,the improvement ranges from 3.56%to 7.31%.The effectiveness of each module is verified through ablation experiments.

关 键 词：注意力机制 隐式反馈 图卷积神经网络 自监督学习 社交推荐 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]