基于信任扩展和列表级排序学习的服务推荐方法

doi:10.11959/j.issn.1000-436x.2018007

通信学报 ›› 2018, Vol. 39 ›› Issue (1): 147-158.doi: 10.11959/j.issn.1000-436x.2018007

基于信任扩展和列表级排序学习的服务推荐方法

方晨^1,²,张恒巍^1,²,张铭^1,²,王晋东^1,²

¹ 信息工程大学三院，河南郑州 450001
² 数字工程与先进计算国家重点实验室，河南郑州 450001

修回日期:2017-12-26 出版日期:2018-01-01 发布日期:2018-02-07
作者简介:方晨（1993-），男，安徽宿松人，信息工程大学硕士生，主要研究方向为服务推荐、数据挖掘等。|张恒巍（1978-），男，河南洛阳人，博士，信息工程大学副教授，主要研究方向为网络安全与攻防对抗、信息安全风险评估。|张铭（1993-），男，河南安阳人，信息工程大学硕士生，主要研究方向为云资源调度。|王晋东（1966-），男，山西洪洞人，信息工程大学教授，主要研究方向为网络与信息安全、云资源管理。
基金资助:
国家自然科学基金资助项目(61303074);国家自然科学基金资助项目(61309013);河南省科技攻关计划基金资助项目(12210231003)

Trust expansion and listwise learning-to-rank based service recommendation method

Chen FANG^1,²,Hengwei ZHANG^1,²,Ming ZHANG^1,²,Jindong WANG^1,²

¹ The Third College,Information Engineering University,Zhengzhou 450001,China
² State Key Laboratory of Mathematical Engineering and Advanced Computing,Zhengzhou 450001,China

Revised:2017-12-26 Online:2018-01-01 Published:2018-02-07
Supported by:
The National Natural Science Foundation of China(61303074);The National Natural Science Foundation of China(61309013);Henan Science and Technology Research Project(12210231003)

摘要/Abstract

摘要：

针对传统基于信任网络的服务推荐算法中信任关系稀疏以及通过QoS预测值排序得到的服务推荐列表不一定最符合用户偏好等问题，提出基于信任扩展和列表级排序学习的服务推荐方法（TELSR）。在分析服务排序位置信息的重要性后给出概率型用户相似度计算方法，进一步提高相似度计算的准确性；利用信任扩展模型解决用户信任关系稀疏性问题，并结合用户相似度给出可信邻居集合构建方法；基于可信邻居集合，利用列表级排序学习方法训练出最优排序模型。仿真实验表明，与已有算法相比，TELSR在具有较高推荐精度的同时，还可有效抵抗恶意用户的攻击。

关键词: 服务推荐, 排序学习, 概率型用户相似度, 信任关系

Abstract:

In view of the problem of trust relationship in traditional trust-based service recommendation algorithm,and the inaccuracy of service recommendation list obtained by sorting the predicted QoS,a trust expansion and listwise learning-to-rank based service recommendation method (TELSR) was proposed.The probabilistic user similarity computation method was proposed after analyzing the importance of service sorting information,in order to further improve the accuracy of similarity computation.The trust expansion model was presented to solve the sparseness of trust relationship,and then the trusted neighbor set construction algorithm was proposed by combining with the user similarity.Based on the trusted neighbor set,the listwise learning-to-rank algorithm was proposed to train an optimal ranking model.Simulation experiments show that TELSR not only has high recommendation accuracy,but also can resist attacks from malicious users.

Key words: service recommendation, learning-to-rank, probabilistic user similarity, trust relationship

中图分类号:

TP393

方晨,张恒巍,张铭,王晋东. 基于信任扩展和列表级排序学习的服务推荐方法[J]. 通信学报, 2018, 39(1): 147-158.

Chen FANG,Hengwei ZHANG,Ming ZHANG,Jindong WANG. Trust expansion and listwise learning-to-rank based service recommendation method[J]. Journal on Communications, 2018, 39(1): 147-158.

图/表 10

图1

图2

表1

图3

图4

图5

表2

图6

表3

图7

参考文献 24

[1]	李玲, 刘敏, 成国庆 . 一种基于FAHP的多维QoS的局部最优服务选择模型[J]. 计算机学报, 2015,38(10): 1997-2010.
	LI L , LIU M , CHENG G Q . A local optimal model of service selection of multi-QoS based on FAHP[J]. Chinese Journal of Computers, 2015,38(10): 1997-2010.
[2]	MA Y , WANG S G , YANG F C ,et al. Predicting QoS values via multi-dimensional QoS data for Web service recommendations[C]// IEEE Conference on Web Services. 2015: 249-256.
[3]	LIU Z , MA J , JIANG Z ,et al. IRLT:integrating reputation and local trust for trustworthy service recommendation in service-oriented social networks[J]. Plos One, 2016,11(3):e0151438.
[4]	张莉, 张斌, 黄利萍 ,等. 基于服务调用特征模式的个性化Web服务QoS预测方法[J]. 计算机研究与发展, 2013,50(5): 1066-1075.
	ZHANG L , ZHANG B , HUANG L P ,et al. A personalized Web service quality prediction approach based on invoked feature model[J]. Journal of Computer Research and Development, 2013,50(5): 1066-1075.
[5]	QI L , DOU W , ZHOU Y ,et al. A context-aware service evaluation approach over big data for cloud applications[J]. IEEE Transactions on Cloud Computing, 2015,PP(99): 1.
[6]	HUANG S S , WANG S Q , LIU T Y ,et al. Listwise collaborative filtering[C]// The 38th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). 2015: 343-352.
[7]	黄震华, 张佳雯, 田春岐 . 基于排序学习的推荐算法研究综述[J]. 软件学报, 2016,27(3): 691-713.
	HUANG Z H , ZHANG J W , TIAN C Q . Survey on learning-to-rank based recommendation algorithms[J]. Journal of Software, 2016,27(3): 691-713.
[8]	GOLDBERG D . Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992,35(12): 61-70.
[9]	PARK C , KIM D , OH J ,et al. TRecSo:enhancing top-k recommendation with social information[C]// International Conference Companion on World Wide Web,International World Wide Web Conferences Steering Committee. 2016: 89-90.
[10]	王海艳, 杨文彬, 王随昌 . 基于可信联盟的服务推荐方法[J]. 计算机学报, 2014,37(2): 301-311.
	WANG H Y , YANG W B , WANG S C . A service recommendation method based on trustworthy community[J]. Chinese Journal of Computers, 2014,37(2): 301-311.
[11]	LIU J , TANG M , ZHENG Z ,et al. Location-aware and personalized collaborative filtering for Web service recommendation[J]. IEEE Transactions on Services Computing, 2015,9(5): 686-699.
[12]	HU Y , PENG Q , HU X . A time-aware and data sparsity tolerant approach for Web service recommendation[C]// IEEE International Conference on Web Services. 2014: 33-40.
[13]	WEI L , YIN J , DENG S ,et al. Collaborative Web service QoS prediction with location-based regularization[C]// IEEE International Conference on Web Services. 2012: 464-471.
[14]	胡堰, 彭启民, 胡晓惠 . 一种基于隐语义概率模型的个性化Web服务推荐方法[J]. 计算机研究与发展, 2014,51(8): 1781-1793.
	HU Y , PENG Q M , HU X H . A personalized Web service recommendation method based on latent semantic probabilistic model[J]. Journal of Computer Research and Development, 2014,51(8): 1781-1793.
[15]	WANG X Y , ZHU J K , ZHENG Z B ,et al. A spatial-temporal QoS prediction approach for time-aware Web service recommendation[J]. ACM Transactions on the Web, 2016,10(1): 1-25.
[16]	WEIMER M , KARATZOGLOU A , LE Q V ,et al. Cofirank maximum margin matrix factorization for collaborative ranking[C]// The 21th Int’l Conference on Neural Information Processing Systems. 2007: 1-8.
[17]	SHI Y , KARATZOGLOU A , BALTRUNAS L ,et al. TFMAP:optimizing MAP for top-n context-aware recommendation[C]// ACM Special Interest Group on Information Retrieval. 2012: 155-164.
[18]	MOLLICA C , TARDELLA L . Bayesian mixture of Plackett-Luce models for partially ranked data[J]. Statistics, 2015,2(4): 208-222.
[19]	CAO Z , QIN T , LIU T Y ,et al. Learning to rank:from pairwise approach to listwise approach[C]// The 2007 ACM conference on Machine learning. 2007: 129-136.
[20]	FANG W , ZHANG C , SHI Z ,et al. BTRES:beta-based trust and reputation evaluation system for wireless sensor networks[J]. Journal of Network ＆ Computer Applications, 2015(59): 88-94.
[21]	郭弘毅, 刘功申, 苏波 ,等. 融合社区结构和兴趣聚类的协同过滤推荐算法[J]. 计算机研究与发展, 2016,53(8): 1664-1672.
	GUO H Y , LIU G S , SU B ,et al. Collaborative filtering recommendation algorithm combining community structure and interest clusters[J]. Journal of Computer Research and Development, 2016,53(8): 1664-1672.
[22]	ZHENG Z B , ZHANG Y L , LYU M R . Distributed QoS evaluation for real-world Web services[C]// The 8th International Conference on Web Services. 2010: 83-90.
[23]	贾冬艳, 张付志 . 基于双重邻居选取策略的协同过滤推荐算法[J]. 计算机研究与发展, 2013,50(5): 1076-1084.
	JIA D Y , ZHANG F Z . A collaborative filtering recommendation algorithm based on double neighbor choosing strategy[J]. Journal of Computer Research and Development, 2013,50(5): 1076-1084.
[24]	LIU J , WU C , XIONG Y ,et al. List-wise probabilistic matrix factorization for recommendation[J]. Information Sciences, 2014(278): 434-447.

IP地址	服务ID	响应时间/ms	数据块大小/KB	HTTP code	HTTP message
35.9.27.26	8 451	2 736	582	200	OK
35.9.27.26	8 460	804	14 419	200	OK
35.9.27.26	8 953	20 176	2 624	?1	TimeoutException
192.33.90.66	8 712	719	631	200	OK

k取值	NDCG@10	运行时间/s
1	0.732 4	2.2
2	0.745 6	5.5
3	0.753 7	9.7

矩阵密度	NDCG	CF-DNC	TACF	listPMF	listCF	TELSR
0.04	NDCG@10	0.663 4(5.57%)	0.672 7(4.12%)	0.674 7(3.81%)	0.692 9(1.08%)	0.700 4
	NDCG@20	0.684 5(4.78%)	0.697 5(2.83%)	0.705 1(1.72%)	0.721 8(?0.64%)	0.717 2
0.08	NDCG@10	0.685 9(6.78%)	0.698 3(4.89%)	0.705 0(3.89%)	0.727 3(0.70%)	0.732 4
	NDCG@20	0.711 1(5.43%)	0.725 5(3.34%)	0.731 0(2.56%)	0.746 1(0.48%)	0.749 7
0.12	NDCG@10	0.692 4(8.11%)	0.708 0(5.73%)	0.717 3(4.37%)	0.738 7(1.34%)	0.748 6
	NDCG@20	0.719 3(6.06%)	0.733 5(4.01%)	0.737 6(3.43%)	0.755 2(1.02%)	0.762 9
0.16	NDCG@10	0.698 8(9.23%)	0.717 1(6.44%)	0.725 2(5.25%)	0.751 1(1.62%)	0.763 3
	NDCG@20	0.723 4(7.66%)	0.739 8(5.27%)	0.745 9(4.41%)	0.768 3(1.37%)	0.778 8
0.20	NDCG@10	0.708 8(10.25%)	0.729 6(7.10%)	0.735 6(6.22%)	0.762 6(2.47%)	0.781 4
	NDCG@20	0.732 9(8.57%)	0.746 4(6.61%)	0.758 7(4.88%)	0.779 4(2.01%)	0.795 7

基于信任扩展和列表级排序学习的服务推荐方法

Trust expansion and listwise learning-to-rank based service recommendation method

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 24

相关文章 5

Metrics

推荐阅读 0

[1]	邢玉萍, 詹永照. 基于Worker权重差分进化与Top-k排序的结果汇聚算法[J]. 通信学报, 2021, 42(1): 27-36.
[2]	赵晨阳,王俊岭. 基于隐含上下文支持向量机的服务推荐方法[J]. 通信学报, 2019, 40(9): 61-73.
[3]	朱敬华,明骞. LBSN中融合信任与不信任关系的兴趣点推荐[J]. 通信学报, 2018, 39(7): 157-165.
[4]	张佩云,陈恩红,黄波. 基于社会网络面向个性化需求的可信服务推荐[J]. 通信学报, 2013, 34(12): 49-59.
[5]	张秀伟,何克清,王健,李征. SaaS服务超市的构建模型和服务推荐方法[J]. 通信学报, 2011, 32(9A): 158-165.