Author(s)

Xiang Li ^1,2, Zhijian Wang ^1*

Affiliation(s)

¹ College of Computer and Information Technology Engineering, Hohai University, Nanjing, 211100, China;

² Faculty of Computer and Software, Huaiyin Institute of Technology, Huaian, 223003, China.

Corresponding Author

Zhijian Wang, email: botsoft@qq.com

ABSTRACT

For the problems of collaborative filtering recommender algorithm, such as it is greatly influenced by the sparse rating data, the data clustering pretreatment is easily trapped in the local optimum in the non-convex sample space, etc, we propose an improved spectral clustering algorithm to optimize the recommender system. Firstly, this method improves the standard spectral clustering algorithm based on the feature difference and orthogonal feature vector, and then the clustering number will automatically determine. Secondly, it uses the improved spectral clustering algorithm to cluster the user and item of the original rating matrix. Thirdly, it fills the missing value for the clustered rating matrix. Finally, it recommends new items for users. By the simulation experiment on Epinions and MovieLents data sets, the results show that this method can effectively alleviate the data sparseness, and improve the prediction accuracy and generalization ability of recommender system.

KEYWORDS

Spectral clustering, recommender system, collaborative filtering, matrix decomposition.

CITE THIS PAPER

Li Xiang,Wang Zhijian. Improved spectral clustering algorithm and its application in recommender system. Journal of Computer Science and Electrical Engineering. 2019, 1(1): 17-15.

REFERENCES

[1]G. Xiong, F.H. Zhu and X.S Dong, A Kind of Novel ITS Based on Space-Air-Ground Big-Data. IEEE Intelligent Transportation Systems Magazine. 8(1) (2016), pp.10-22.

[2]J. P. Shim, J. Koh and S. Fister, Phonetic Analytics Technology and Big Data: Real-World Cases. Communications of the ACM. 59(2) (2016), pp.84-90.

[3]R. Canas, G. Santos and M. Juan, A Recommender System for Non-traditional Educational Resources: A Semantic Approach. Journal of Universal Computer Science. 21(2) (2015) pp. 306-325.

[4]M.T. Ribeiro, Ziviani  Nivio and Edleno Silva, Multiobjective Pareto-Efficient Approaches for Recommender Systems. ACM Transactions on Intelligent Systems and Technology. 5(4) (2015), pp. 38-52.  

[5]F. Lin, X. Zhou and W.H. Zeng, Online Learning for Collaborative Filtering. International Journal of Computers Communications & Control. 11(2) (2016), pp. 248-258.

[6]W.K. Pan and M. Zhong, Interaction-Rich Transfer Learning for Collaborative Filtering with Heterogeneous User Feedback. IEEE Intelligent Systems. 29(6) (2014), pp. 48-54.

[7]M.Y. Komkhao, J. Lu and Z. Li, Incremental Collaborative Filtering Based on Mahalanobis Distance and Fuzzy Membership for Recommender Systems. International Journal of General Systems. 42(1) (2013), pp. 41-46.

[8] B. Sarwar, G. Karypis and J.A. Konstan, Application of dimensionality reduction in recommender system-a case study．Minneapolis: Minnesota Univ Minneapolis Dept of Computer Science,2000.

[9] H. Ji, J. Li and C. Ren,  Hybrid collaborative filtering model for improved recommendation. 2013 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI). Dongguan: IEEE, 2013: 142-145.

[10] Y. Koren, Collaborative filtering with temporal dynamics.In: Proc.of the ACM SIGKDD Conf.on Knowledge Discovery and Data Mining. ACM Press,2009.89-97. 

[11]L. Baltrunas, B. Ludwig and F. Ricci, Matrix factorization techniques for context-aware recommendation. Proceedings of the fifth ACM conference on Recommender systems,2011:301-304. 

[12] B.Y. Zou, C.P. Li and L.W. Tan, Social Recommendations Based on User Trust and Tensor Factorization. Journal of Software,25(12) (2014):2852-2864.

[13] Z. Wang, Y. Wang and H. Wu, Tags meet ratings:Improving collaborative filtering with tag-based neighborhood method. Proceedings of the Workshop on Social Recommender Systems,2010:1-9.

[14]C.Q. Huang, A Modified Fuzzy C-Mean Algorithm for Automatic Clustering Number, Applied Mechanics and Materials, 333(2013):1418-1421.

[15]D. Sharmilarani, N . Kousika, G. Komarasamy. Modified K-Means Algorithm for Automatic Stimation of Number of Clusters Using Advanced Visual Assessment of Cluster Tendency. 8th IEEE International Conference on Intelligent Systems and Control (ISCO),2014:236-239.

[16]S.Y. Lin, C.Y. Lai and C.H. Wu, A Trustworthy QoS-based Collaborative Filtering Approach for Web Service Discovery. Journal of Systems and Software. 93(2014), pp. 217-228.

[17]C. Andrew, L. Zhang and D. Agarwal, Collaborative Filtering for Massive Multinomial Data. Journal of Applied Statistics. 41(4) (2014), pp. 701-715.

[18]M.B. Xiao and X.W. Zheng. Collaborative Filtering Algorithm with Stepwise Prediction. Application Research of Computers, 32(11) (2015), pp. 3256-3272.

[19]H. Wu, Y.J. Wang and Z. Wang, Two-Phase Collaborative Filtering Algorithm Based on Co-Clustering. Journal of Software, 21(5) (2010), pp. 1042-1054.

[20]H.C. Zhao, L.L. Zhai and S.C. Zhang, A Collaborative Filtering Recommendation Method Based on Clustering of Gray Association Degree and Factors of Tag Overlap. Computer Engineering & Science, 38(1) (2016), pp. 171-175.

[21]H.X. Zhao, X.H. Wang and J.P. Yang, Mixed Collaborative Recommendation Algorithm Based on Factor Analysis of User and Item. Journal of Computer Applications, 31(5) (2011), pp. 1382-1386.

[22]Z. Huang, D. Zeng and H.C. Chen, A Comparison of Collaborative-filtering Recommendation Algorithms for E-commerce. IEEE Intelligent Systems, 22(5) (2007), pp. 68-78.

[23]Y. Yang, Z.G. Ma and Y. Yang, Multitask Spectral Clustering by Exploring Intertask Correlation. IEEE Transactions on Cybernetics, 45(5) (2015), pp. 1083-1094.

[24]M.A. Oikawa, Z. Diasm and G. Siome, Manifold Learning and Spectral Clustering for Image Phylogeny Forests. IEEE Transactions on Information Forensics and Security, 11(1) (2016), pp. 5-18.

[25]S.B. Fatemi, M.R. Mobasheriv and A.A. Abkar, Clustering Multispectral Images Using Spatial–Spectral Information. IEEE Geoscience and Remote Sensing Letters, 12(7) (2015), pp. 1521-1525.

[26]B. Tandianus, H. Johan and H.S. Seah, Spectral Caustic Rendering of A Homogeneous Caustic Object Based on Wavelength Clustering and Eye Sensitivity. The Visual Computer, 31(3) (2015), pp. 365-370.

[27]S. Mehrkanoon, C. Alzate and R. Mall,  Multiclass Semisupervised Learning Based Upon Kernel Spectral Clustering. IEEE Transactions on Neural Networks and Learning Systems, 26(4) (2015), pp. 720-733.

[28]J. Liu, C. Wu, and Y. Xiong, List-Wise Probabilistic Matrix Factorization for Recommendation. Information Sciences, 278(2014), pp. 434–447.

[29]K. Jarvelin, J. Kekalainen. Ir evaluation methods for retrieving highly relevant documents, in: Proceedings of 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, in SIGIR ’00, ACM, New York, NY, USA, 2000, pp.41-48.

[30]O. Chapelle, D. Metlzer, Y. Zhang. Expected Reciprocal Rank for Graded Relevance. Proceedings of the 18th ACM conference on Information and knowledge management, in: CIKM ’09, ACM New York, NY, USA, 2009, pp.621-630.

[31]X.K. Zhou, S. Wu and Chen, kNN Processing with Co-space Distance in SoLoMo Systems. Expert Systems with Applications, 41(16) (2014), pp. 6967-6982.

[32]A. Saleh, E. Desoulw and H. Shereen, Promoting the Performance of Vertical Recommendation Systems by Applying New Classification Techniques. Knowledge Based Systems, 75(20156), pp. 192-223.

[33]J.J. Huang, X. Yuan and N. Zhong, Modeling Tag-Aware Recommendations Based on User Preferences. International Journal of Information Technology & Decision Making, 14(5) (2015), pp. 947-970.

[34]W. Liu, C. Wu and B. Feng, Conditional Preference in Recommender Systems. Expert Systems with Applications, 42 (2) (2015), pp. 774–788.

[35]J. Liu, Y. Xiong and C. Wu, Learning Conditional Preference Networks from Inconsistent Examples, IEEE Transactions on Knowledge & Data Engineering, 26 (2) (2014), pp. 376–390.

[36]J. Liu, Z. Yao and Y. Xiong, W. Liu, Learning Conditional Preference Network from Noisy Samples Using Hypothesis Testing, Knowledge-Based Systems, 40 (1) (2013), pp. 7-16.

[37]H.S. Le and T.M. Tuan, General Factorization Framework for Context-aware Recommendations, Data Mining and Knowledge Discovery, 30 (2) (2016), pp. 342-371.

[38]J. Liu, C.H. Sui and D. Deng, Representing Conditional Preference by Boosted Regression Trees for Recommendation. Information Sciences, 327(2016), pp. 1-20.

[39]Z. Gantner, S. Rendle and C. Freudenthaler, et al. Mymedialite: A Free Recommender System Library, In: Proceedings of the 15th ACM Conference on Recommender Systems, in: RecSys’11, ACM, New York, NY, USA, 2011,pp. 305–308.

[40]Z. Cao, T. Qin and T.Y. Liu, Learning to Rank: From Pairwise Approach to Listwise Approach. Proceedings of the 24th International Conference on Machine Learning, in: ICML ’07, ACM, New York, NY, USA,2007, pp. 129–136.