Recommendation algorithm based on improved spectral clustering and transfer learning
- 313 Downloads
Collaborative filtering (CF) recommendation has made great success in solving information overload. However, CF has some disadvantages such as cold start, data sparseness, low operation efficiency and knowledge cannot transfer between multiple rating matrixes. In this paper, we propose a recommendation algorithm based on improved spectral clustering and transfer learning (RAISCTL) to improve the forecasting accuracy and generalization ability of recommender system. RAISCTL firstly improves the spectral clustering by using the eigenvalue differences and orthogonal eigenvectors and realizes the automatic determination of cluster numbers. In addition, the improved spectral clustering algorithm is used to cluster the two dimensions of the users and items of the original rating matrix. Then, RAISCTL decomposes the rating matrix after clustering and gets the sharing group rating matrix. Finally, RAISCTL makes rating forecasting and recommendations based on the sharing group rating matrix and transfer learning. The simulation results show that RAISCTL can effectively improve the recommendation accuracy and generalization ability compared with other 8 conventional CF approaches.
KeywordsSpectral clustering Recommendation algorithm Recommender systems Collaborative filtering Transfer learning
This work is supported by University Science Research Project of Jiangsu Province (15KJB520004), Science and Technology Projects of Huaian (HAC201601), Science and Technology Project of Jiangsu Province (BE2015127), Jiangsu Government Scholarship for Overseas Studies, Jiangsu QingLan Project and Top-notch Academic Programs Project of Jiangsu Higher Education Institutions.
- 2.Xiong G, Zhu FH, Dong XS (2016) Semantics-aware content-based recommender systems: design and architecture guidelines. Neurocomputing 254(SI):79–85Google Scholar
- 10.Xiao MB, Zheng XW (2015) Collaborative filtering algorithm with stepwise prediction. Appl Res Comput 32(11):3256–3272Google Scholar
- 14.Yu J, Yang XK, Gao F (2016) Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans Cybern 99:1–11Google Scholar
- 18.Meng XF, Ci X (2013) Big data management: concepts, techniques and challenges. J Comput Res Dev 50(1):146–169Google Scholar
- 23.Saya Y, Yasunari Y, Chikoto K (2013) Music recommendation hybrid system for improving recognition ability using collaborative filtering and impression words. Artif Life Robot 18(1):109–116Google Scholar
- 31.Li B, Yang Q, Xue XY (2009) Transfer learning for collaborative filtering via a rating-matrix generative model. In: Proceedings of the 26th international conference on machine learning (ICML 2009), Montreal, Canada, 14–18 June, pp 617–624Google Scholar
- 33.Agni D, Herve J, Laurent A (2014) Image retrieval with reciprocal and shared nearest neighbors. In: 2014 international conference on computer vision theory and applications (VISAPP) 2, pp 321–328Google Scholar
- 34.Luiz P, Tomasz R, Joshua A (2013) Recommending people to people: the nature of reciprocal recommenders with a case study in online dating. User Model User Adapt Interact 23(5):477–488Google Scholar
- 44.Gantner Z, Rendle S, Freudenthaler C (2011) Mymedialite: a free recommender system library. In: Proceedings of the 15th ACM conference on recommender systems, RecSys’11, ACM, New York, NY, USA, pp 305–308Google Scholar