面向隐式反馈的标签感知推荐方法

doi:10.11896/j.issn.1002-137X.2019.04.006

摘要/Abstract

摘要： 为进一步提高面向隐式反馈的标签感知推荐性能,针对隐式反馈数据的稀疏性问题以及标签数据的冗余、语义模糊等问题,提出了一种基于用户细粒度偏好和增量加权矩阵分解的个性化推荐方法。为缓解隐式反馈数据稀疏不平衡的影响,提出使用协同近邻用户关系从大规模未观测数据中挖掘目标用户可能感兴趣的潜在项目,即近邻用户感兴趣但目标用户未选择的项目,进而提出了用户对项目的细粒度偏好假设:观测项目>潜在项目>其他未观测项目,改进传统成对偏好假设的粗糙性。为获取更为可靠的近邻用户,利用基于深度学习的方法来抽取用户-标签的低维、抽象的深层语义特征,缓解了原始标签数据的冗余、语义模糊等对用户表征的影响。最后,基于用户的细粒度偏好提出一种增量加权矩阵分解模型,并进行快速优化求解与推荐。实验结果表明:提出的算法在多个排序推荐准确性的评价指标(Pre@5,NDCG@5,MRR)上分别提升了约9%,8%,9%,验证了所提算法的有效性。

Abstract: In order to further improve the performance of tag-aware personalized recommendation with implicit feedbacks,aiming at the problems of the redundancy,ambiguity of tagging information and the sparsity and imbalance of implicit feedbacks,this paper proposed a personalized recommendation method based on fine-grained preference assumption and augmented weighted matrix factorization.First,one kind of candidate items that the target user may prefer are mined by leveraging its neighbor user,which are preferred by neighbor users which have not been selected by the target user.Thus,a type of fine-grained preference relationship among three kinds of items for target users is obtained,i.e.,observed item>candidate item>other unobserved data.This kind of operation can help to alleviate the sparsity and imbalance problem.Then,the deep learning method is used to extract the in-depth semantic features from tag space.In this way,representations of users’ profiles become more abstract and advanced,and user neighbors are obtained based on the in-depth semantic features.Afterwards,a revised weighted matrix factorization model is formulated based on the fine-grained preference relationship for personalized recommendation.And a fast eALS algorithm is used for model optimization in terms of low time complexity.Experiments on real-world datasets show that the proposed method outperforms competing methods on several evaluation metrics,including Pre@5,NDCG@5,MRR.The three indicators are respectively increased by 9%,8%,and 9%,which indicates the effectiveness of the proposed methods.

Key words: Implicit feedback, Tag-aware recommendation, Deep learning, Fine-grained preference, Weighted matrix factorization

中图分类号:

TP391.3

李红梅, 刁兴春, 曹建军, 冯钦, 张磊. 面向隐式反馈的标签感知推荐方法[J]. 计算机科学, 2019, 46(4): 36-43.

LI Hong-mei, DIAO Xing-chun, CAO Jian-jun, FENG Qin, ZHANG Lei. Tag-aware Recommendation Method with Implicit Feedback[J]. Computer Science, 2019, 46(4): 36-43.

参考文献

[1]HU Y,KOREN Y,VOLINSKY C.Collaborative filtering for
implicit feedback datasets[C]∥ Proceedings of the 8th International Conference on Data Mining.2008.
[2]PAN R,ZHOU Y,CAO B,et al.One-Class Collaborative Filte-
ring[C]∥International Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases.2008.
[3]HE X,ZHANG H,KAN M Y,et al.Fast Matrix Factorization
for Online Recommendation with Implicit Feedback[C]∥ Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.2016:549-558.
[4]PAN W,ZHONG H,XU C,et al.Adaptive Bayesian persona-
lized ranking for heterogeneous implicit feedbacks[J].Know-ledge-Based Systems,2015,73(1):173-180.
[5]SHEPITSEN A,GEMMELL J,MOBASHER B,et al.Persona-
lized recommendation in social tagging systems using hierarchical clustering[C]∥Proceeding of the 2008 ACM Conference on Recommendater Systems.2008:259-266.
[6]ZUO Y,ZENG J,GONG M,et al.Tag-aware recommender systems based on deep neural networks[J].Neurocomputing,2016,204:51-60.
[7]ZHANG Z K,ZHOU T,ZHANG Y C.Personalized recommendation via integrated diffusion on user-item-tag tripartite graphs[J].Physica A:Statistical Mechanics and its Applications,2010,389(1):179-186.
[8]ZHANG Z,ZENG D D,ABBASI A,et al.A Random Walk
Model for Item Recommendation in Social Tagging Systems[J].Acm Transactions on Management Information Systems,2013,4(2):1-24.
[9]HE M,YANG F,YAO K S,et al.TEFRCF:Collaborative filtering personalized recommendation algorithm based on tag entropy feature representation[J].Computer Science,2018,45(6):465-486.(in Chinese)
何明,杨芃,要凯升,等.TEFRCF:标签熵特征表示的协同过滤个性化推荐算法[J].计算机科学,2018,45(6):465-486.
[10]ZENG D,LI H.How Useful Are Tags? — An Empirical Analysis of Collaborative Tagging for Web Page Recommendation[C]∥IEEE Isi 2008 Paisi,Paccf,and Soco International Workshops on Intelligence and Security Informatics.2008:320-330.
[11]HE M,YAO K S,YANG F,et al.Collaborative filtering perso-
nalized recommendation based on similarity of tag information feature[J].Computer Science,2018,45(6):415-422.(in Chinese)
何明,要凯升,杨芃,等.基于标签信息特征相似性的协同过滤个性化推荐[J].计算机科学,2018,45(6):415-422.
[12]WU L,CHEN E,LIU Q,et al.Leveraging tagging for neighborhood-aware probabilistic matrix factorization[C]∥ Proceedings of the 21st ACM International Conference on Information and Knowledge Management.2012:1854-1858.
[13]MA H,ZHOU T C,LYU M R,et al.Improving Recommender Systems by Incorporating Social Contextual Information[J].ACM Transactions on Information Systems,2011,29(2):1-23.
[14]ZHANG Z,ZENG D D,ABBASI A,et al.A random walk model for item recommendation in social tagging systems[J].ACM Transactions on Management Information Systems,2013,4(2):1-24.
[15]LI H Y,FU Y Q.Collaborative filtering recommendation algorithm based on tag clustering and item topic[J].ComputerScie-nce,2018,45(4):247-251.(in Chinese)
李昊阳,符云清.基于标签权重评分的推荐模型及算法研究[J].计算机科学,2018,45(4):247-251.
[16]ELKAHKY A M,SONG Y,HE X.A multi-view deep learning approach for cross domain user modeling in recommendation systems[C]∥WWW’15.2015:278-288.
[17]HUANG P S,HE X,GAO J,et al.Learning deep structured semantic models for web search using clickthrough data[C]∥ ACM International Conference on Conference on Information & Knowledge Management.2013:2333-2338.
[18]HUANG L W,JIANG B T,LV S Y,et al.Survey on deep lear-
ning based recommender systems[J].Chinese Journal of Compu-ters,2018,427(7):191-219.(in Chinese)
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[J].计算机学报,2018,427(7):191-219.
[19]LE Q V,NGIAM J,COATES A,et al.On optimization methods for deep learning[C]∥ International Conference on Machine Learning(ICML 2011).Bellevue,Washington,USA,2011:265-272.
[20]HINTON G E.A Practical Guide to Training Restricted Boltz-
mann Machines[J].Momentum,2012,9(1):599-619.
[21]SEDHAIN S,MENON A K,SANNER S,et al.On the effectiveness of linear models for one-class collaborative filtering[C]∥ Proceedings of the 30th Conference on Artificial Intelligence.2016.
[22]LI H,GE Y,HONG R,et al.Point-of-Interest Recommenda-
tions:Learning Potential Checkins from Friends[C]∥Procee-dings of the 22nd International ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2016.
[23]DEVOOGHT R,KOURTELLIS N,MANTRACH A.Dynamic matrix factorization with priors on unknown values[C]∥ Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2015:189-198.
[24]DEVOOGHT R,KOURTELLIS N,MANTRACH A.Dynamic Matrix Factorization with Priors on Unknown Values[C]∥ Proceedings of the 21st International ACM SIGKDD Conference on Knowledge Discovery and Data Mining Sydney.NSW,Australia,2015.
[25]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.BPR:Bayesian Personalized Ranking from Implicit Feedback[C]∥ Proceedings of the 25th Conferenceon Uncertainty in Artificial Intelligence.2009:452-461.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed