To improve low robustness and reconstruction accuracy of recommendation system, a semi-supervised preference learning algorithm is proposed to obtain potential preferences via preference learning and implement recommendations. The l2,1 norm is utilized as the regularization of the optimization objective function to eliminate the noises and outliers. The graph Laplacian regularization is employed to integrate the side information of UI matrix to realize multi-image fusion and improve recommendation precision. The experiments on Movielens 10M and Netflix datasets indicate that the proposed algorithm produces high precision, speed and robustness.
[1] MEHTA B, HOFMANN T, NEJDL W. Robust Collaborative Filtering // Proc of the ACM Conference on Recommender Systems. New York, USA: ACM, 2007: 49-56.
[2] CHENG Z P, HURLEY N. Robust Collaborative Recommendation by Least Trimmed Squares Matrix Factorization // Proc of the 22nd IEEE International Conference on Tools with Artificial Intelligence. Washington, USA: IEEE, 2010: 105-112.
[3] ZHANG F Z, SUN S X. A Robust Collaborative Recommendation Algorithm Based on Least Median Squares Estimator. Journal of Computers, 2014, 9(2): 308-314.
[4] DING C H Q, LI T, JORDAN M I. Convex and Semi-nonnegative Matrix Factorizations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(1): 45-55.
[5] LIU H F, WU Z H, CAI D, et al. Constrained Nonnegative Matrix Factorization for Image Representation. IEEE Transactions on Pa-ttern Analysis and Machine Intelligence, 2012, 34(7): 1299-1311.
[6] CHIANG K Y, DHILLON I S, HSIEH C J. Using Side Information to Reliably Learn Low-Rank Matrices from Missing and Corrupted Observations. Journal of Machine Learning Research, 2018, 19: 1-35.
[7] 雷恒鑫,刘惊雷.基于行列联合选择矩阵分解的偏好特征提取.模式识别与人工智能, 2017, 30(3): 279-288.
(LEI H X, LIU J L. Preference Feature Extraction Based on Column Union Row Matrix Decomposition. Pattern Recognition and Artificial Intelligence, 2017, 30(3): 279-288.)
[8] CANDÈS E J, PLAN Y. Matrix Completion with Noise. Proceedings of the IEEE, 2010, 98(6): 925-936.
[9] LI Z C, LIU J, TANG J H. Robust Structured Subspace Learning for Data Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(10): 2085-2098.
[10] DEBRUYNE M, HUBERT M, SUYKENS J A K. Model Selection in Kernel Based Regression Using the Influence Function. Journal of Machine Learning Research, 2008, 9: 2377-2400.
[11] HUBERT M, ROUSSEEUW P J. ROBPCA: A New Approach to Robust Principal Component Analysis. Technometrics, 2005, 47(1): 64-79.
[12] ZHAO Z, ZHANG L J, HE X F. Expert Finding for Question Answering via Graph Regularized Matrix Completion. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(4): 993-1004.
[13] SHANG F H, JIAO L C, WANG F. Graph Dual Regularization Non-negative Matrix Factorization for Co-clustering. Pattern Recognition, 2012, 45(6): 2237-2250.
[14] HUANG S D, WANG H J, LI T, et al. Robust Graph Regularized Nonnegative Matrix Factorization for Clustering. Data Mining and Knowledge Discovery, 2018, 32(2): 483-503.
[15] CHEN Y, JALALI A, SANGHAVI S, et al. Clustering Partially Observed Graphs via Convex Optimization. Journal of Machine Learning Research, 2014, 15: 2213-2238.
[16] NIE F P, XU D, TSANG I W. Flexible Manifold Embedding: A Framework for Semi-supervised and Unsupervised Dimension Reduction. IEEE Transactions on Image Processing, 2010, 19(7): 1921-1932.
[17] MACKEY L, TALWALKAR A, JORDAN M I. Distributed Matrix Completion and Robust Factorization. Journal of Machine Learning Research, 2015, 16: 913-960.
[18] CANDÈS E J, RECHT B. Exact Matrix Completion via Convex Optimization. Foundations of Computational Mathematics, 2009, 9(6): 717-772.
[19] HUANG J, NIE F P, HUANG H. Robust Manifold Nonnegative Matrix Factorization. ACM Transactions on Knowledge Discovery from Data, 2014, 8(3). DOI: 10.1145/2601434.
[20] ZHANG F Z, LU Y L, CHEN J M, et al. Robust Collaborative Filtering Based on Non-negative Matrix Factorization and R1-norm. Knowledge-Based Systems, 2017, 118: 177-190.
2019, Vol. 32 
