基于异质用户网络嵌入的服务推荐方法研究
|
摘要
服务推荐过程中,为充分利用用户标签标注关系与用户的社交关系信息,提升推荐结果的准确性,提出一种基于异质用户网络嵌入的方法,通过将用户节点映射为一个低维的向量,再利用得到的用户向量进行协同推荐。在公开数据集Delicious上进行了实证分析,实验结果表明,相对已有的2个方法,该方法的推荐精度可分别提高18.1%和16.6%,且发现在学习用户表征向量时,节点之间的直接关系与"朋友的朋友"关系对表示用户节点结构信息同等重要;同时,推荐过程中为目标用户返回的相似用户在25个最为适宜。
In order to make full use of user's tagging and social relationship information and improve the accuracy of recommendation results in service recommendation, we propose a new recommendation method based on heterogeneous user network embedding. It maps a user node to a low-dimensional vector, and then utilizes the obtained user vector to carry out collaborative recommendation. We verify the method on Delicious, a public dataset. Experimental results show that our method outperforms the two existing methods, and the recommended accuracy is increased by 18.1% and 16.6% respectively. Furthermore, the results also suggest that the direct relationship between nodes is as important as the "friends of friends" relationship in representing user node structural information when learning the user representation vector. At the same time, it is most suitable to return top 25 similar users for the target user in the recommendation process.
In order to make full use of user's tagging and social relationship information and improve the accuracy of recommendation results in service recommendation, we propose a new recommendation method based on heterogeneous user network embedding. It maps a user node to a low-dimensional vector, and then utilizes the obtained user vector to carry out collaborative recommendation. We verify the method on Delicious, a public dataset. Experimental results show that our method outperforms the two existing methods, and the recommended accuracy is increased by 18.1% and 16.6% respectively. Furthermore, the results also suggest that the direct relationship between nodes is as important as the "friends of friends" relationship in representing user node structural information when learning the user representation vector. At the same time, it is most suitable to return top 25 similar users for the target user in the recommendation process.
引文
[1] Kohi A,Ebrahimi S J,Jalali M.Improving the accuracy and efficiency of tag recommendation system by applying hybrid methods[C]//Proc of International Conference on Computer and Knowledge Engineering,2011:242-248.
[2] Zhang Bin,Zhang Yin,Gao Ke-ning,et al.Social label recommendation of fusion relation and content analysis [J].Journal of Software,2012,23(3):476-488.(in Chinese)
[3] Rendle S,Freudenthaler C,Gantner Z,et al.BPR:Bayesian personalized ranking from implicit feedback[C]//Proc of Conference on Uncertainty in Artificial Intelligence,2009:452-461.
[4] Jamali M,Ester M.A matrix factorization technique with trust propagation for recommendation in social networks[C]//Proc of ACM Conference on Recommender Systems,2010:135-142.
[5] Jamali M,Ester M.TrustWalker:A random walk model for combining trust-based and item-based recommendation[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,2009:397-406.
[6] Lu W,Ioannidis S,Bhagat S,et al.Optimal recommendations under attraction,aversion,and social influence[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,2014:811-820.
[7] Ma H,King I,Lyu M R.Learning to recommend with explicit and implicit social relations[J].ACM Transactions on Intelligent Systems & Technology,2011,2(3):1-19.
[8] Chen X,Liu X,Huang Z,et al.RegionKNN:A scalable hybrid collaborative filtering algorithm for personalized web service recommendation[C]//Proc of the IEEE International Conference on Web Services,2010:9-16.
[9] Wang X,Lu W,Ester M,et al.Social Recommendation with strong and weak ties[C]//Proc of the 25th ACM International Conference on Information and Knowledge Management,2016:5-14.
[10] Bhuiyan T.Online survey on trust and interest similarity[M]//Trust for Intelligent Recommendation,New York:Springer New York,2013.
[11] Shao L,Zhang J,Wei Y,et al.Personalized QoS prediction for web services via collaborative filtering[C]//Proc of IEEE International Conference on Web Services,2007:439-466.
[12] Hu Q Y,Zhao Z L,Wang C D,et al.An item orientated recommendation algorithm from the multi-view perspective[J].Neurocomputing,2017,269:261-272.
[13] Moraru A,Fortuna C,Fortuna B,et al.A hybrid approach to QoS-aware web service classification and recommendation[C]//Proc of IEEE International Conference on Intelligent Computer Communication & Processing,2009:343-346.
[14] Ren L,Wang W.An SVM-based collaborative filtering approach for Top-N web services recommendation[J].Future Generation Computer Systems,2018(78):531-543.
[15] Deng S,Huang L,Xu G .Social network-based service recommendation with trust enhancement[J].Expert Systems with Applications,2014,41(18):8075-8084.
[16] Zeng D,Li H.How useful are tags?—An empirical analysis of collaborative tagging for web page recommendation[C]//Proc of IEEE Isi Paisi,Paccf,& Soco International Workshops on Intelligence & Security Informatics,2008:320-330.
[17] Sen S,Vig J,Riedl J.Tagommenders:Connecting users to items through tags[C]//Proc of International Conference on World Wide Web,2009:671-680.
[18] Zhao S,Du N,Nauerz A,et al.Improved recommendation based on collaborative tagging behaviors[C]//Proc of International Conference on Intelligent User Interfaces,2008:413-416.
[19] Givon S,Lavrenko V.Predicting social-tags for cold start book recommendations[C]//Proc of ACM Conference on Recommender Systems,2009:333-336.
[20] Liu J,Wu C,Liu W.Bayesian probabilistic matrix factorization with social relations and item contents for recommendation[J].Decision Support Systems,2013,55(3):838-850.
[21] Yu Yan,Qiu Guang-hua.Research on collaborative filtering recommendation algorithm by fusing social network[J].New Technology of Library & Information Service,2012(6):54-59.(in Chinese)
[22] Guo L,Ma J,Chen Z,et al.Learning to recommend with social relation ensemble[C]//Proc of ACM International Conference on Information & Knowledge Management,2012:2599-2602.
[23] Wang C,Blei D M.Collaborative topic modeling for recommending scientific articles[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2011:448-456.
[24] Covington P,Adams J,Sargin E.Deep neural networks for YouTube recommendations[C]//Proc of ACM Conference on Recommender Systems,2016:191-198.
[25] Okura S,Tagami Y,Ono S,et al.Embedding-based news recommendation for millions of users[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,2017:1933-1942.
[26] Vasile F,Smirnova E,Conneau A.Meta-Prod2Vec:Product embeddings using side-information for recommendation[C]//Proc of ACM Conference on Recommender Systems,2016:225-232.
[27] Han X,Shi C,Zheng L,et al.Representation learning with depth and breadth for recommendation using multi-view data[C]//Proc of Asia-Pacific Web,2018:181-188.
[28] Seo S,Huang J,Yang H,et al.Interpretable convolutional neural networks with dual local and global attention for review rating prediction[C]//Proc of the 8th ACM Conference on Recommender Systems,2017:297-305.
[29] Tang J,Qu M,Wang M,et al.LINE:Large-scale information network embedding[C]//Proc of International World Wide Web Conferences Steering Committee,2015:1067-1077.
[30] Grover A,Leskovec J.node2vec:Scalable feature learning for networks[C]//Proc of ACM International Conference on Knowledge Discovery & Data Mining,2016:1-10.
[2] 张斌,张引,高克宁,等.融合关系与内容分析的社会标签推荐[J].软件学报,2012,23(3):476-488.
[21] 俞琰,邱广华.融合社会网络的协同过滤推荐算法研究[J].现代图书情报技术,2012(6):54-59.
[2] Zhang Bin,Zhang Yin,Gao Ke-ning,et al.Social label recommendation of fusion relation and content analysis [J].Journal of Software,2012,23(3):476-488.(in Chinese)
[3] Rendle S,Freudenthaler C,Gantner Z,et al.BPR:Bayesian personalized ranking from implicit feedback[C]//Proc of Conference on Uncertainty in Artificial Intelligence,2009:452-461.
[4] Jamali M,Ester M.A matrix factorization technique with trust propagation for recommendation in social networks[C]//Proc of ACM Conference on Recommender Systems,2010:135-142.
[5] Jamali M,Ester M.TrustWalker:A random walk model for combining trust-based and item-based recommendation[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,2009:397-406.
[6] Lu W,Ioannidis S,Bhagat S,et al.Optimal recommendations under attraction,aversion,and social influence[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,2014:811-820.
[7] Ma H,King I,Lyu M R.Learning to recommend with explicit and implicit social relations[J].ACM Transactions on Intelligent Systems & Technology,2011,2(3):1-19.
[8] Chen X,Liu X,Huang Z,et al.RegionKNN:A scalable hybrid collaborative filtering algorithm for personalized web service recommendation[C]//Proc of the IEEE International Conference on Web Services,2010:9-16.
[9] Wang X,Lu W,Ester M,et al.Social Recommendation with strong and weak ties[C]//Proc of the 25th ACM International Conference on Information and Knowledge Management,2016:5-14.
[10] Bhuiyan T.Online survey on trust and interest similarity[M]//Trust for Intelligent Recommendation,New York:Springer New York,2013.
[11] Shao L,Zhang J,Wei Y,et al.Personalized QoS prediction for web services via collaborative filtering[C]//Proc of IEEE International Conference on Web Services,2007:439-466.
[12] Hu Q Y,Zhao Z L,Wang C D,et al.An item orientated recommendation algorithm from the multi-view perspective[J].Neurocomputing,2017,269:261-272.
[13] Moraru A,Fortuna C,Fortuna B,et al.A hybrid approach to QoS-aware web service classification and recommendation[C]//Proc of IEEE International Conference on Intelligent Computer Communication & Processing,2009:343-346.
[14] Ren L,Wang W.An SVM-based collaborative filtering approach for Top-N web services recommendation[J].Future Generation Computer Systems,2018(78):531-543.
[15] Deng S,Huang L,Xu G .Social network-based service recommendation with trust enhancement[J].Expert Systems with Applications,2014,41(18):8075-8084.
[16] Zeng D,Li H.How useful are tags?—An empirical analysis of collaborative tagging for web page recommendation[C]//Proc of IEEE Isi Paisi,Paccf,& Soco International Workshops on Intelligence & Security Informatics,2008:320-330.
[17] Sen S,Vig J,Riedl J.Tagommenders:Connecting users to items through tags[C]//Proc of International Conference on World Wide Web,2009:671-680.
[18] Zhao S,Du N,Nauerz A,et al.Improved recommendation based on collaborative tagging behaviors[C]//Proc of International Conference on Intelligent User Interfaces,2008:413-416.
[19] Givon S,Lavrenko V.Predicting social-tags for cold start book recommendations[C]//Proc of ACM Conference on Recommender Systems,2009:333-336.
[20] Liu J,Wu C,Liu W.Bayesian probabilistic matrix factorization with social relations and item contents for recommendation[J].Decision Support Systems,2013,55(3):838-850.
[21] Yu Yan,Qiu Guang-hua.Research on collaborative filtering recommendation algorithm by fusing social network[J].New Technology of Library & Information Service,2012(6):54-59.(in Chinese)
[22] Guo L,Ma J,Chen Z,et al.Learning to recommend with social relation ensemble[C]//Proc of ACM International Conference on Information & Knowledge Management,2012:2599-2602.
[23] Wang C,Blei D M.Collaborative topic modeling for recommending scientific articles[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2011:448-456.
[24] Covington P,Adams J,Sargin E.Deep neural networks for YouTube recommendations[C]//Proc of ACM Conference on Recommender Systems,2016:191-198.
[25] Okura S,Tagami Y,Ono S,et al.Embedding-based news recommendation for millions of users[C]//Proc of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,2017:1933-1942.
[26] Vasile F,Smirnova E,Conneau A.Meta-Prod2Vec:Product embeddings using side-information for recommendation[C]//Proc of ACM Conference on Recommender Systems,2016:225-232.
[27] Han X,Shi C,Zheng L,et al.Representation learning with depth and breadth for recommendation using multi-view data[C]//Proc of Asia-Pacific Web,2018:181-188.
[28] Seo S,Huang J,Yang H,et al.Interpretable convolutional neural networks with dual local and global attention for review rating prediction[C]//Proc of the 8th ACM Conference on Recommender Systems,2017:297-305.
[29] Tang J,Qu M,Wang M,et al.LINE:Large-scale information network embedding[C]//Proc of International World Wide Web Conferences Steering Committee,2015:1067-1077.
[30] Grover A,Leskovec J.node2vec:Scalable feature learning for networks[C]//Proc of ACM International Conference on Knowledge Discovery & Data Mining,2016:1-10.
[2] 张斌,张引,高克宁,等.融合关系与内容分析的社会标签推荐[J].软件学报,2012,23(3):476-488.
[21] 俞琰,邱广华.融合社会网络的协同过滤推荐算法研究[J].现代图书情报技术,2012(6):54-59.