An improved recommendation algorithm via weakening indirect linkage effect

doi:10.1088/1674-1056/24/7/078901

中国物理B ›› 2015, Vol. 24 ›› Issue (7): 78901-078901.doi: 10.1088/1674-1056/24/7/078901

• INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY • 上一篇下一篇

An improved recommendation algorithm via weakening indirect linkage effect

陈光, 邱天, 沈小泉

School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China

收稿日期:2014-10-24 修回日期:2015-02-02 出版日期:2015-07-05 发布日期:2015-07-05
基金资助:
Project supported by the National Natural Science Foundation of China (Grant No. 11175079) and the Young Scientist Training Project of Jiangxi Province, China (Grant No. 20133BCB23017).

An improved recommendation algorithm via weakening indirect linkage effect

Chen Guang (陈光), Qiu Tian (邱天), Shen Xiao-Quan (沈小泉)

School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China

Received:2014-10-24 Revised:2015-02-02 Online:2015-07-05 Published:2015-07-05
Contact: Qiu Tian E-mail:tianqiu.edu@gmail.com
Supported by:
Project supported by the National Natural Science Foundation of China (Grant No. 11175079) and the Young Scientist Training Project of Jiangxi Province, China (Grant No. 20133BCB23017).

摘要/Abstract

摘要： We propose an indirect-link-weakened mass diffusion method (IMD), by considering the indirect linkage and the source object heterogeneity effect in the mass diffusion (MD) recommendation method. Experimental results on the MovieLens, Netflix, and RYM datasets show that, the IMD method greatly improves both the recommendation accuracy and diversity, compared with a heterogeneity-weakened MD method (HMD), which only considers the source object heterogeneity. Moreover, the recommendation accuracy of the cold objects is also better elevated in the IMD than the HMD method. It suggests that eliminating the redundancy induced by the indirect linkages could have a prominent effect on the recommendation efficiency in the MD method.

关键词: bipartite network, mass diffusion, recommender system, indirect linkage effect

Abstract: We propose an indirect-link-weakened mass diffusion method (IMD), by considering the indirect linkage and the source object heterogeneity effect in the mass diffusion (MD) recommendation method. Experimental results on the MovieLens, Netflix, and RYM datasets show that, the IMD method greatly improves both the recommendation accuracy and diversity, compared with a heterogeneity-weakened MD method (HMD), which only considers the source object heterogeneity. Moreover, the recommendation accuracy of the cold objects is also better elevated in the IMD than the HMD method. It suggests that eliminating the redundancy induced by the indirect linkages could have a prominent effect on the recommendation efficiency in the MD method.

Key words: bipartite network, mass diffusion, recommender system, indirect linkage effect

中图分类号: (Networks and genealogical trees)

89.75.Hc

87.23.Ge (Dynamics of social systems) 05.70.Ln (Nonequilibrium and irreversible thermodynamics)

陈光, 邱天, 沈小泉. An improved recommendation algorithm via weakening indirect linkage effect[J]. 中国物理B, 2015, 24(7): 78901-078901.

Chen Guang (陈光), Qiu Tian (邱天), Shen Xiao-Quan (沈小泉). An improved recommendation algorithm via weakening indirect linkage effect[J]. Chin. Phys. B, 2015, 24(7): 78901-078901.

参考文献 36

[1]	Adomavicius J and Tuzhilin A 2005 IEEE Trans. Knowl. Data Eng. 17 734
[2]	Goldberg D, Nichols D, Oki B M and Terry D 1992 Commun. ACM 35 61
[3]	Schafer J B, Frankowski D, Herlocker J and Sen S 2007 The Adaptive Web (Berlin Heidelberg: Springer) p. 291
[4]	Breese J S, Heckerman D and Kadie C 1998 Proc. 14th Conf. Uncertainity Artif. Intel (Morgan Kaufmann Publishers Inc.) p. 43
[5]	Hofmann T 2007 Proc. 26th Ann Intl SIGIR Conf Research Devel (Berlin Heidelberg: Springer) p. 259
[6]	Ren J, Zhou T and Zhang Y C 2008 EPL 82 58007
[7]	Pazzani M J and Billsus D 2007 The Adaptive Web (Berlin Heidelberg: Springer) p. 325
[8]	Lipczak M, Hu Y, Kollet Y and Milios E 2009 ECML PKDD Discovery Challenge p. 157
[9]	Cantador I, Vallet D and Jose J M 2009 TECML PKDD Discovery Challenge p. 17
[10]	Ju S and Hwang K B 2009 Proc. the ECML/PKDD 2009 Discovery Challenge Workshop p. 109
[11]	Zhang Z K, Zhou T and Zhang Y C 2010 Physica A 389 179
[12]	Shang M S, Zhang Z K, Zhou T and Zhang Y C 2010 Physica A 389 1259
[13]	Zhang Z K, Liu C, Zhang Y C and Zhou T 2010 EPL 92 28002
[14]	Zhang Z K and Liu C 2012 Int J. Bifurcat. Chaos 22 1250166
[15]	Kim H N, Ji A T, Ha I and Jo G S 2010 Electron Commerce Research Appl. 9 73
[16]	Zhang Z K, Zhou T and Zhang Y C 2011 J. Comput. Sci. Technol. 26 767
[17]	Lü L Y, Medo M, Yeung C H, Zhang Y C, Zhang Z K and Zhou T 2012 Phys. Rep. 519 1
[18]	Bai M, Hu K and Tang Y 2011 Chin. Phys. B 20 128902
[19]	Watts D J and Strongatz S H 1998 Nature 393 440
[20]	Barabàsi A L and Albert R 1999 Science 286 509
[21]	Zhang Y C, Blattner M and Yu Y K 2007 Phys. Rev. Lett. 99 154301
[22]	Zhou T, Ren J, Medo M and Zhang Y C 2007 Phys. Rev. E 76 046115
[23]	Liu J G, Zhou T and Guo Q 2011 Phys. Rev. E 84 037101
[24]	Qiu T, Wang T T, Zhang Z K, Zhong L X and Chen G 2013 EPL 104 48007
[25]	Zhou T, Kuscsik Z, Liu J G, Medo M, Wakeling J R and Zhang Y C 2010 Proc. Natl. Acad. Sci. USA 107 4511
[26]	Qiu T, Chen G, Zhang Z K and Zhou T 2011 EPL 95 58003
[27]	Qiu T, Zhang Z K and Chen G 2013 PLoS One 8 e63531
[28]	Zhou T, Jiang L L, Su R Q and Zhang Y C 2008 EPL 81 58004
[29]	Liu C and Zhou W X 2012 Physica A 391 5704
[30]	Zhou T, Su R Q, Liu R R, Jiang L L, Wang B H and Zhang Y C 2009 New J. Phys. 11 123008
[31]	Qiu T, Han T Y, Zhong L X, Zhang Z K and Chen G 2014 Computer Phys. Commun. 185 489
[32]	Holme P, Liljeros F, Edling C R and Kim B J 2003 Phys. Rev. E 68 056107
[33]	Chen H B, Fan Y, Fang J Q and Di Z R 2009 Acta Phys. Sin. 58 1383 (in Chinese)
[34]	Herlocker J L, Konstan J A, Terveen L G and Riedl J T 2004 ACM T. Inform. Syst. 22 5
[35]	Lü L Y and Liu W P 2011 Phys. Rev. E 83 066119
[36]	Lam X N, Vu T, Le T D and Duong A D 2008 Proceedings of the 2nd International Conference on Ubiquitous Information Management and Communication p. 208

An improved recommendation algorithm via weakening indirect linkage effect

An improved recommendation algorithm via weakening indirect linkage effect

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献 36

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	Yun-Dong Tang(汤云东), Jian Zou(邹建), Rodolfo C C Flesch(鲁道夫 C C 弗莱施), Tao Jin(金涛), and Ming-Hua He(何明华). Thermal apoptosis analysis considering injection behavior optimization and mass diffusion during magnetic hyperthermia[J]. 中国物理B, 2022, 31(1): 14401-014401.
[2]	吴果林, 顾长贵, 邱路, 杨会杰. A uniform framework of projection and community detection for one-mode network in bipartite networks[J]. 中国物理B, 2017, 26(12): 128901-128901.