基于异构邻域聚合的协同过滤推荐算法

doi:10.16451/j.cnki.issn1003-6059.202108004

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (757 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要传统的协同过滤算法使用one-hot编码生成的特征向量信息量稀少,对异构行为数据仅挖掘不同行为间的联系而忽略用户间行为的联系.针对上述问题,文中提出基于异构邻域聚合的协同过滤推荐算法.首先,使用图对用户和项目的异构交互进行建模,并利用图的连通特性构建邻域.然后,使用轻量级图卷积方法整合邻域信息,融入目标用户和目标项目的特征向量.最后,将融合邻域信息的用户与项目的特征向量输入多任务异构网络进行训练,通过丰富特征向量信息的方法缓解数据稀疏问题.在数据集上的实验证实文中算法的性能较优.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	夏鸿斌
	陆炜
	刘渊

关键词 ：异构数据, 邻域聚合, 协同过滤, 推荐系统, 图神经网络

Abstract：In traditional collaborative filtering models, the feature vector generated by one-hot encoding is sparsely informative. Heterogeneous behavior data is only employed to describe the relationship between different behaviors and the relationship between behaviors of different users is ignored.Aiming at these problems, an algorithm of collaborative filtering with heterogeneous neighborhood aggregation is proposed. Firstly, the heterogeneous interaction between users and items is modeled by the graph, and neighborhoods are built through the connectivity of graph. Then, the neighborhood information integrated by the lightweight graph convolution method is merged into the feature vectors of the target users and items. Finally, the feature vectors of users and items integrating with neighborhood information are input into a multi-task heterogeneous network for training. The problem of data sparseness is alleviated by enriching the hidden information of feature vectors. Experiments on the datasets prove that the performance of the proposed model is better.

Key words： Heterogeneous Data Neighborhood Aggregation Collaborative Filtering Recommender System Graph Neural Network

收稿日期: 2021-05-13

ZTFLH:

TP 391

基金资助:国家自然科学基金项目(No.61972182)资助

通讯作者: 夏鸿斌,博士,副教授,主要研究方向为个性化推荐、自然语言处理、网络优化.E-mail:hbxia@163.com.

作者简介: 陆炜,硕士研究生,主要研究方向为深度学习、推荐系统.E-mail:1051183356@qq.com.刘渊,硕士,教授,主要研究方向为网络安全、社交网络.E-mail:lyuan1800@sina.com.

引用本文:

夏鸿斌, 陆炜, 刘渊. 基于异构邻域聚合的协同过滤推荐算法[J]. 模式识别与人工智能, 2021, 34(8): 712-722. XIA Hongbin, LU Wei, LIU Yuan. Collaborative Filtering with Heterogeneous Neighborhood Aggregation. , 2021, 34(8): 712-722.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202108004 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2021/V34/I8/712

[1] 罗洋,夏鸿斌,刘渊.融合注意力LSTM的协同过滤推荐算法.中文信息学报, 2019, 33(12): 110-118.
(LUO Y, XIA H B, LIU Y. Collaborative Filtering Based on Attention LSTM. Journey of Chinese Information Processing, 2019, 33(12): 110-118.)
[2] 黄立威,江碧涛,吕守业,等.基于深度学习的推荐系统研究综述.计算机学报, 2018, 41(7): 1619-1647.
(HUANG L W, JIANG B T, LÜ S Y, et al. Survey on Deep Lear-ning Based Recommender Systems. Chinese Journal of Computers, 2018, 41(7): 1619-1647.)
[3] ADOMAVICIUS G, TUZHILIN A. Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(6): 734-749.
[4] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian Personalized Ranking from Implicit Feedback // Proc of the 25th Conference on Uncertainty in Artificial Intelligence. New York, USA: ACM, 2009: 452-461.
[5] HE X N, LIAO L Z, ZHANG H W, et al. Neural Collaborative Filtering // Proc of the 26th International Conference on World Wide Web. New York, USA: ACM, 2017: 173-182.
[6] EBESU T, SHEN B, FANG Y. Collaborative Memory Network for Recommendation Systems // Proc of the 41st ACM SIGIR International Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2018: 515-524.
[7] KABBUR S, NING X, KARYPIS G. FISM: Factored Item Similarity Models for Top-N Recommender Systems // Proc of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2013: 659-667.
[8] CHEN J Y, ZHANG H W, HE X N, et al. Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention // Proc of the 40th ACM SIGIR International Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2017: 335-344.
[9] MA C, MA L H, ZHANG Y X, et al. Memory Augmented Graph Neural Networks for Sequential Recommendation // Proc of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019, 34(4): 5045-5052.
[10] QU Y R, BAI T, ZHANG W N, et al. An End-to-End Neighborhood-Based Interaction Model for Knowledge-Enhanced Recommendation // Proc of the 1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data. New York, USA: ACM, 2019. DOI: 10.1145/3326937.3341257.
[11] WANG X, HE X N, WANG M, et al. Neural Graph Collaborative Filtering // Proc of the 42nd ACM SIGIR International Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2019: 165-174.
[12] HE X N, DENG K, WANG X, et al. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation // Proc of the 43rd ACM SIGIR International Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2020: 639-648.
[13] CHONG C, ZHANG M, LIU Y, et al. Neural Attentional Rating Regression with Review-Level Explanations // Proc of the 28th International Conference on World Wide Web. New York, USA: ACM, 2018: 1583-1592.
[14] 陈碧毅,黄玲,王昌栋,等.融合显式反馈与隐式反馈的协同过滤推荐算法.软件学报, 2020, 31(3): 794-805.
(CHEN B Y, HUANG L, WANG C D, et al. Explicit and Implicit Feedback Based Collaborative Filtering Algorithm. Journal of Software, 2020, 31(3): 794-805.)
[15] ZHAO Z, CHENG Z Y, HONG L C, et al. Improving User Topic Interest Profiles by Behavior Factorization // Proc of the 24th International Conference on World Wide Web. New York, USA: ACM, 2015: 1406-1416.
[16] GAO C, HE X N, GAN D H, et al. Neural Multi-task Recommendation from Multi-behavior Data // Proc of the 35th IEEE International Conference on Data Engineering. Washington, USA: IEEE, 2019: 1554-1557.
[17] CHEN C, ZHANG M, ZHANG Y F, et al. Efficient Heteroge-neous Collaborative Filtering without Negative Sampling for Reco-mmendation. Proceeding of the AAAI Conference on Artificial Intelligence, 2020, 34(1): 19-26.
[18] YUAN F J, XIN X, HE X N, et al. f_BGD: Learning Embeddings from Positive Unlabeled Data with BGD[C/OL]. [2021-05-01]. https://fajieyuan.github.io/papers/fBGD2018.pdf.
[19] WANG X, WANG R J, SHI C, et al. Multi-component Graph Convolutional Collaborative Filtering[C/OL]. [2021-05-01]. https://arxiv.org/pdf/1911.10699.pdf.
[20] KIP F T N, WELLING M. Semi-supervised Classification with Graph Convolutional Networks[C/OL]. [2021-05-01]. https://arxiv.org/pdf/1609.02907v4.pdf.
[21] LIU N, SHEN B. Aspect-Based Sentiment Analysis with Gated Alternate Neural Network. Knowledge-Based Systems, 2019, 188. DOI: 10.1016/j.knosys.2019.105010.
[22] WANG X, JIN H Y, ZHANG A, et al. Disentangled Graph Co-llaborative Filtering // Proc of the 43rd ACM SIGIR International Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2020: 1001-1010.
[23] CHEN H, ZHANG M, LIU Y Q, et al. Social Attentional Memory Network: Modeling Aspect- and Friend-Level Differences in Re-commendation // Proc of the 12th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2019: 177-185.
[24] LIANG D W, CHARLIN L, MCINERNEY J, et al. Modeling User Exposure in Recommendation // Proc of the 25th International Conference on World Wide Web. New York, USA: ACM, 2016: 951-961.
[25] HARPER F M, KONSTAN J A. The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems, 2016, 5(4): 19:1-19:19.
[26] ZHU H, LI X, ZHANG P Y, et al. Learning Tree-Based Deep Model for Recommender Systems // Proc of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2018: 1079-1088.
[27] LONI B, PAGANO R, LARSON M, et al. Bayesian Personalized Ranking with Multi-channel User Feedback // Proc of the 10th ACM Conference on Recommender Systems. New York, USA: ACM, 2016: 361-364