An initialization method to improve the training time of matrix factorization algorithm for fast recommendation. (English) Zbl 1498.65063
Summary: Recommendation systems are successful personalizing tools and information filtering in web. One of the most important recommendation methods is matrix factorization method. In matrix factorization method, the latent features of users and items are determined in such a way that the inner product of the latent features of a user with the latent features of an item is equal to that user’s rating on that item. This model is solved using alternate optimization algorithm. The solution and the prediction error of this algorithm depend on the initial values of the latent features of users which are usually set to small random values. The purpose of this paper is to propose a fast alternate optimization algorithm for matrix factorization which converges to a good solution. To do so, firstly, we show experimentally that if the latent feature vector of each user is initialized by a vector of which elements are equal, we can also obtain a proper solution using the alternate optimization algorithm. Then, we prove that if our proposed initialization method is used, the alternate optimization algorithm for matrix factorization can be simplified using Sherman-Morrison formula. Experimental results on 5 real datasets show that the runtime of our proposed algorithm is 2-45 times less than the traditional method.
MSC:
| 65F99 | Numerical linear algebra |
| 15A23 | Factorization of matrices |
| 68T35 | Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence |
Keywords:
matrix factorization; recommendation system; initialization method; Sherman-Morrison formulaReferences:
| [1] | Bertsekas, D., Nonlinear programming, (optimization and computation) (2016), New York: Athena Scientific, New York · Zbl 0935.90037 |
| [2] | Bobadilla, J.; Alonso, S.; Hernando, AJAS, Deep learning architecture for collaborative filtering recommender systems, Appl Sci, 10, 7, 2441 (2020) · doi:10.3390/app10072441 |
| [3] | Bu, J.; Shen, X.; Xu, B.; Chen, C.; He, X.; Cai, D., Improving collaborative recommendation via user-item subgroups, IEEE Trans Knowl Data Eng, 28, 9, 2363-2375 (2016) · doi:10.1109/TKDE.2016.2566622 |
| [4] | Cai, W., Neighborhood-enhanced transfer learning for one-class collaborative filtering, Neurocomputing, 341, 80-87 (2019) · doi:10.1016/j.neucom.2019.03.016 |
| [5] | Chae, D-K; Lee, S-C; Lee, S-Y; Kim, S-W, On identifying k-nearest neighbors in neighborhood models for efficient and effective collaborative filtering, Neurocomputing, 278, 134-143 (2018) · doi:10.1016/j.neucom.2017.06.081 |
| [6] | Chen, J.; Wang, C.; Shi, Q.; Feng, Y.; Chen, C., Social recommendation based on users’ attention and preference, Neurocomputing, 341, 1-9 (2019) · doi:10.1016/j.neucom.2019.02.045 |
| [7] | Condli MK, Lewis DD, Madigan D, Posse C (1999) Bayesian mixed-e ects models for recommender systems. In: ACM SIGIR. p 99 |
| [8] | Deepa, N.; Pandiaraja, PJSC, Hybrid context aware recommendation system for E-health care by Merkle Hash tree from cloud using evolutionary algorithm, Soft Comput, 24, 1-13 (2019) |
| [9] | Demšar, J., Statistical comparisons of classifiers over multiple data sets, J Mach Learn Res, 7, 1, 1-30 (2006) · Zbl 1222.68184 |
| [10] | Gholami, A.; Forghani, Y.; Branch, M., Improving multi-class co-clustering-based collaborative recommendation using item tags improving multi-class co-clustering-based collaborative recommendation using item tags, Rev d’Intell Artif, 34, 59-65 (2020) |
| [11] | Goodfellow I, Sulthana S, Ming M (2014) Generative adversarial nets. In: Advances in neural information processing systems. pp 2672-2680 |
| [12] | Hasanzadeh, N.; Forghani, Y., Improving the accuracy of M-distance based nearest neighbor recommendation system by using ratings variance, Ingénierie Syst Inf, 24, 2, 131-137 (2019) |
| [13] | Jain, G.; Mahara, T.; Tripathi, KN; Suzuki, Y.; Ovaska, SJ; Furuhashi, T.; Roy, R.; Dote, Y., A survey of similarity measures for collaborative filtering-based recommender system, Soft computing: theories and applications, 343-352 (2020), Berlin: Springer, Berlin · doi:10.1007/978-981-15-0751-9_32 |
| [14] | Khadem, MM; Forghani, Y., A recursive algorithm to increase the speed of regression-based binary recommendation systems, Inf Sci, 512, 1324-1334 (2020) · doi:10.1016/j.ins.2019.10.072 |
| [15] | Kumar, V.; Pujari, AK; Sahu, SK; Kagita, VR; Padmanabhan, V., Collaborative filtering using multiple binary maximum margin matrix factorizations, Inf Sci, 380, 1-11 (2017) · Zbl 1429.68225 · doi:10.1016/j.ins.2016.11.003 |
| [16] | Kumar, V.; Pujari, AK; Sahu, SK; Kagita, VR; Padmanabhan, V., Proximal maximum margin matrix factorization for collaborative filtering, Pattern Recognit Lett, 86, 62-67 (2017) · doi:10.1016/j.patrec.2016.12.016 |
| [17] | Lara-Cabrera, R.; González-Prieto, Á.; Ortega, FJAS, Deep matrix factorization approach for collaborative filtering recommender systems, Appl Sci, 10, 14, 4926 (2020) · doi:10.3390/app10144926 |
| [18] | Lemire D, Maclachlan A (2005) Slope one predictors for online rating-based collaborative filtering. In: Proceedings of the 2005 SIAM international conference on data mining, Newport Beach. SIAM, pp 471-475 |
| [19] | Li J, Sun L, Wang J (2011) A slope one collaborative filtering recommendation algorithm using uncertain neighbors optimizing. In: International conference on web-age information management. Springer, Berlin, pp 160-166 |
| [20] | Liu, D.; Ye, XJK-BS, A matrix factorization based dynamic granularity recommendation with three-way decisions, Knowl Based Syst, 191, 105243 (2020) · doi:10.1016/j.knosys.2019.105243 |
| [21] | Liu, J.; Pan, W.; Ming, Z., CoFiGAN: Collaborative filtering by generative and discriminative training for one-class recommendation, Knowl Based Syst, 191, 105255 (2020) · doi:10.1016/j.knosys.2019.105255 |
| [22] | Pan, Y.; He, F.; Yu, H., A novel enhanced collaborative autoencoder with knowledge distillation for top-N recommender systems, Neurocomputing, 332, 137-148 (2019) · doi:10.1016/j.neucom.2018.12.025 |
| [23] | Park, Y.; Park, S.; Jung, W.; Lee, S-G, Reversed CF: a fast collaborative filtering algorithm using a k-nearest neighbor graph, Expert Syst Appl, 42, 8, 4022-4028 (2015) · doi:10.1016/j.eswa.2015.01.001 |
| [24] | Qi, J.; Qian, T.; Wei, L., The connections between three-way and classical concept lattices, Knowl Based Syst, 91, 1, 143-151 (2016) · doi:10.1016/j.knosys.2015.08.006 |
| [25] | Ren, L.; Wang, W., An SVM-based collaborative filtering approach for Top-N web services recommendation, Future Gener Comput Syst, 78, 1, 531-543 (2018) · doi:10.1016/j.future.2017.07.027 |
| [26] | Salter, J.; Antonopoulos, N., CinemaScreen recommender agent: combining collaborative and content-based filtering, IEEE Intell Syst, 21, 1, 35-41 (2006) · doi:10.1109/MIS.2006.4 |
| [27] | Sulthana, AR; Gupta, M.; Subramanian, S.; Mirza, SJSC, Improvising the performance of image-based recommendation system using convolution neural networks and deep learning, Soft Comput, 24, 1-14 (2020) · doi:10.1007/s00500-020-04803-0 |
| [28] | Van Meteren R, Van Someren M (2000) Using content-based filtering for recommendation. In: Proceedings of the machine learning in the new information age: MLnet/ECML2000 workshop, Barcelona. pp 47-56 |
| [29] | Vapnik, V., The nature of statistical learning (1995), New York: Springer, New York · Zbl 0833.62008 · doi:10.1007/978-1-4757-2440-0 |
| [30] | Wang, Q-X; Luo, X.; Li, Y.; Shi, X-Y; Gu, L.; Shang, M-SJN, Incremental slope-one recommenders, Neurocomputing, 272, 1, 606-618 (2018) · doi:10.1016/j.neucom.2017.07.033 |
| [31] | Wang, D., Elastic-net regularized latent factor analysis-based models for recommender systems, Neurocomputing, 329, 66-74 (2019) · doi:10.1016/j.neucom.2018.10.046 |
| [32] | Xing, S.; Liu, FA; Wang, Q.; Zhao, X.; Li, T., A hierarchical attention model for rating prediction by leveraging user and product reviews, Neurocomputing, 332, 417-427 (2019) · doi:10.1016/j.neucom.2018.12.027 |
| [33] | Yadalam TV, Gowda VM, Kumar VS, Girish D, Namratha M (2020) Career recommendation systems using content based filtering. In: 2020 5th international conference on communication and electronics systems (ICCES). IEEE, pp 660-665 |
| [34] | Yao, Y., Three-way decisions with probabilistic rough sets, Inf Sci, 180, 3, 341-353 (2010) · doi:10.1016/j.ins.2009.09.021 |
| [35] | Yao Y (2015) Rough sets and three-way decisions. In: International conference on rough sets and knowledge technology, Tianjin. Springer, pp 62-73 · Zbl 1444.68250 |
| [36] | Yuan, Y.; Luo, X.; Shang, M-S, Effects of preprocessing and training biases in latent factor models for recommender systems, Neurocomputing, 275, 1, 2019-2030 (2018) · doi:10.1016/j.neucom.2017.10.040 |
| [37] | Zheng, M.; Min, F.; Zhang, H-R; Chen, W-B, Fast recommendations with the m-distance, IEEE Access, 4, 1, 1464-1468 (2016) · doi:10.1109/ACCESS.2016.2549182 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
