由於精確預測用戶興趣，矩陣分解（MF）技術已廣泛用於推薦系統中。先前的基於MF的方法通過從用戶和項目中提取潛在因素來調整總體評級以提出建議。但是，在實際應用中，人們的喜好通常隨時間而變化。傳統的基於MF的方法無法正確捕獲用戶興趣的變化。在本文中，通過結合MF和長短期記憶（LSTM），我們開發了一種新穎的推薦系統ELR，可以有效地描述用戶的偏好隨時間的演變。基於提出的虛擬交流學習概念，提出了融合進化學習和虛擬交流進化學習兩種學習模型，以捕獲進化模式並預測未來的用戶偏好。實驗結果表明，ELR比其他最新的推薦算法性能更好。此外，我們在幾個現實世界的數據集上進行了實驗，以證明擬議的ELR的實用性。

Matrix factorization (MF) technique has been widely utilized in recommendation systems due to the precise prediction of user interests. Prior MF-based methods adapt the overall rating to make the recommendation by extracting latent factors from users and items. However, in real applications, people’s preferences usually vary with time; the traditional MF-based methods could not properly capture the variation of user interests. In this paper, by combining the MF and Long short-term memory (LSTM), we developed a novel recommendation system, ELR, to effectively describe the preference evolution of users over time. Based on the proposed virtual-communicated learning concept, two learning models, fusing-evolution learning and virtual-communicated-evolution learning, are proposed to capture the evolution pattern and predict the user preference in the future. The experimental results show that ELR performs better than other state-of-the-art recommendation algorithms. In addition, we conduct the experiments on several real world datasets to demonstrate the practicability of proposed ELR.

Table of Contents
Chapter 1 Introduction	1
Chapter 2 Related Works	6
2.1	 Matrix Factorization	6
2.2	 Recommendation on MF	8
Chapter 3 Proposed Recommendation System: ELR	11
3.1       Preliminary	11
3.2	 Feedback sequence transformation & cumulative matrix factorization	12
	(Definition 1 Feedback Matrix and Sequence)	12
	(Definition 2 Preference and Characteristic Matrices)	14
3.3	 Evolution learning	15
	Fusing-Evolution Learning	16
	Virtual-Communicated-Evalution Learning	19
	Model Training	23
3.4	 Prediction Module of ELR	25
Chapter 4 Performance Evaluation	26
4.1	 Experiment Setup	27
4.2	 Analysis on Accuracy Performance	29
4.3	 Comparing Model on over Performance	32
4.4	 Effectiveness of Variation Transition Contexts	33
4.5	 Effectiveness of Virtual Communication Moderation	35
4.6	 Discussion on Parameter Settings	38
Chapter 5 Conclusion	42
Reference	44


List of Figures

Fig. 1: The example rating matrix with preference evolution	1
Fig. 2: The architecture of ELR system	12
Fig. 3: The example of cumulative matrix factorization	15
Fig. 4: The concept of fusing-evolution learning.	17
Fig. 5: The concept of virtual-communicated-evolution learning.	21
Fig. 6: The performance comparison of ELR-VLSTM delta on different K	35
Fig. 7: The performance comparison of different communication layers	37
Fig. 8: The performance comparison of different layers stack on diverse dataset	38
Fig. 9: The performance comparison of different batch size on diverse dataset	39
Fig. 10: The performance comparison of different learning rate on diverse dataset	40
Fig. 11: The performance comparison of different units size on diverse dataset	40
Fig. 12: The performance comparison of different K	41


List of Tables

Table 1: The MovieLens Datasets	27
Table 2: ACC@d Performance of Different Models on real Datasets	31
Table 3: RMSE@d Performance of Different Models on real Datasets	31
Table 4: MAE@d Performance of Different Models on real Datasets	33

M. Abdi, G. Okeyo and R. Mwangi, “Matrix Factorization Techniques for Context-Aware Collaborative Filtering Recommender Systems: A Survey,” Computer and Information Science, vol. 11, no. 2, 2018. 

Y. Chen, Y. Chu, L. Hui, S. Chen, T. Thaipisutikul and K. Weng, “A Novel Evolution-Based Recommendation System,” Proceedings of the IEEE 12th International Conference on Ubi-Media (Umedia 2019), 2019. 

F. Chua, R. Oentaryo and E. Lim, “Modeling Temporal Adoptions Using Dynamic Matrix Factorization,” Proceedings of the IEEE 13th International Conference on Data Mining (ICDM), pp. 91-100, 2013. 

Y. Du, C. Xu and D. Tao, “Privileged Matrix Factorization for Collaborative Filtering,” Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), pp. 1610-1616, 2017. 

R. Gemulla, E. Nijkamp, P. Haas and Y. Sismanis, “Large-scale matrix factorization with distributed stochastic gradient descent,” Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining (SIGKDD), pp. 69-77, 2011. 

J. He, X. Li, L. Liao, D. Song, and K. Cheung, “Inferring a personalized next point-of-interest recommendation model with latent behavior patterns,” Proceedings of the 13th AAAI Conference on Artificial Intelligence (AAAI 2016), pp. 137-143, 2016. 

X. He, H. Zhang, M. Kan and T. Chua, “Fast matrix factorization for online recommendation with implicit feedback,” Proceedings of the 39th International ACM Conference on Research and Development in Information Retrieval (SIGIR), pp. 549-558, 2016. 

S. Huang, M. Xu, M. Xie, M. Sugiyama, G. Niu and S. Chen, “Active Feature Acquisition with Supervised Matrix Completion,” Proceedings of the 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), pp. 1571-1579, 2018. 

M. Jamali and M. Ester, “A Matrix Factorization Technique with Trust Propagation for Recommendation in Social Networks,” Proceedings of the 4th ACM Conference on Recommender Systems (RecSys), pp. 135-142, 2010. 

J. Kawale, H. Bui, B. Kveton, L. Thanh and S. Chawla, “Efficient Thompson Sampling for Online Matrix-Factorization Recommendation,” Proceedings of the 29th Conference on Neural Information Processing Systems (NIPS), pp. 1297–1305, 2015. 

Y. Koren, R. Bell, and C. Volinsky, “Matrix Factorization Techniques for Recommender Systems,” IEEE Computer, vol. 42, pp. 30-37, 2009. 

D. Lee and H. Seung, “Algorithms for Non-negative Matrix Factorization,“ Proceedings of the 13th Advances in Neural Information Processing (NIPS 2000), pp. 535–541. 2000. 

D. Liang, J. Altosaar, L. Charlin and D. Blei, “Factorization Meets the Item Embedding: Regularizing Matrix Factorization with Item Co-occurrence,” Proceedings of the 10th ACM Conference on Recommender Systems (RecSys), pp. 59-66, 2016. 

C. Lin, L. Wang, K. Tsai, “Hybrid Real-Time Matrix Factorization for Implicit Feedback Recommendation Systems,” IEEE Access, 6: 21369-21380, pp. 21369 – 21380, 2018. 

X. Luo, M. Zhou, Y. Xia and Q. Zhu, “An Efficient Non-Negative Matrix-Factorization-Based Approach to Collaborative Filtering for Recommender Systems,” IEEE Transactions on Industrial Informatics, vol. 10, issue: 2, pp. 1273-1284, 2014. 

W. Ma, Y. Wu, M. Gong, C. Qin and S. Wang, “Local Probabilistic Matrix Factorization for Personal Recommendation,” Proceedings of the 13th International Conference on Computational Intelligence and Security (CIS), pp. 97-101, 2017. 

H. Ma, H. Yang, M. Lyu and I. King, “SoRec: social recommendation using probabilistic matrix factorization,” Proceedings of the 17th ACM conference on Information and knowledge management (CIKM), pp. 931-940, 2008. 

R. Mehta and K. Rana, “A review on matrix factorization techniques in recommender systems,” Proceedings of the the 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA 2017), pp. 269-274, 2017. 

Q. Meng, H. Zhu, K. Xiao and H. Xiong, “Intelligent Salary Benchmarking for Talent Recruitment: A Holistic Matrix Factorization Approach,” Proceedings of the IEEE 18th International Conference on Data Mining (ICDM), pp. 337-346, 2018. 

N. Nghe, L. Drumond, T. Horváth, A. Nanopoulos, and L. Thieme, “Matrix and Tensor Factorization for predicting Student Performance,” Proceedings of the 3rd International Conference on Computer Supported Education (CSEDU), vol. 1, pp. 69-78, 2011. 

H. Park, J. Jung and U. Kang, “A Comparative Study of Matrix Factorization and Random Walk with Restart in Recommender Systems,” Proceedings of the IEEE International Conference on Big Data (IEEE BigData), pp. 756-765, 2017. 

R. Salakhutdinov and A. Mnih, “Probabilistic Matrix Factorization,” Proceedings of the ACM 20th International Conference on Neural Information Processing Systems (NIPS), pp. 1257-1264, 2007. 

N. Sorkunlu, D. Luong and V. Chandola, “dynamicMF: A Matrix Factorization Approach to Monitor Resource Usage in High Performance Computing Systems,” Proceedings of the IEEE International Conference on Big Data (IEEE BigData), 2018. 

T. Tran, K. Lee, Y. Liao and D. Lee, “Regularizing Matrix Factorization with User and Item Embeddings for Recommendation,” Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM), pp. 687-696, 2018. 

G. Trigeorgis, K. Bousmalis, S. Zafeiriou and B. Schuller, “A Deep Matrix Factorization Method for Learning Attribute Representations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, issue: 3, pp. 417-429, 2017. 

J. Tu, G. Yu, C. Domeniconi, J. Wang, G. Xiao and M. Guo, “Multi-Label Answer Aggregation based on Joint Matrix Factorization,” Proceedings of the IEEE 18th International Conference on Data Mining (ICDM), pp. 517-526, 2018.  

T. Wallace, C. Godwin, J. Thomson, and A. Tjernlund “The Definitive Guide to Selling on Amazon,” BigCommerce, pp. 1-229, 2019. 

C. Wang, Q. Liu, R. Wu, E. Chen, C. Liu, X. Huang and Z. Huang, “Confidence-Aware Matrix Factorization for Recommender Systems,” Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), pp. 434-442, 2018. 

Q. Wang, P. Tan and J. Zhou, “Imputing Structured Missing Values in Spatial Data with Clustered Adversarial Matrix Factorization,” Proceedings of the IEEE 18th International Conference on Data Mining (ICDM), pp. 1284-1289, 2018. 

Q. Wu and C. Pu, “Modeling and implementing collaborative editing systems with transactional techniques,” Proceedings of the 6th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing (CollaborateCom 2010), pp. 1-10, 2010. 

Z. Wu, H. Tian, X. Zhu, and S. Wang, “Optimization Matrix Factorization Recommendation Algorithm Based on Rating Centrality,” Third International Conference on Data Mining and Big Data (DMBD), LNCS 10943, pp. 114-125, 2018. 

L. Xiong, X. Chen, T. Huang, J. Schneider, and J. Carbonell, “Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization,” Proceedings of the 2010 SIAM International Conference on Data Mining (SDM 2010), pp. 211-222, 2010. 

J. Yoo and S. Choi, “Probabilistic matrix tri-factorization,” Proceeding of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2009), pp. 1553-1556, 2009. 

H. Yu, H. Huang, I. Dihillon and C. Lin, “A Unified Algorithm for One-Cass Structured Matrix Factorization with Side Information,” Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), pp. 2845-2851, 2017. 

V. Yuvaraj and N. SivaKumar, “A Semi- Non-Negative Matrix Factorization and Principal Component Analysis Unified Framework for Data Clustering,” International Journal of Advanced Research in Science, Engineering and Technology (IJARSET), vol. 5, pp. 2-6, issue 1, 2018. 

G. Zeng, H. Zhu, Q. Liu, P. Luo, E. Chen and T. Zhang, “Matrix Factorization with Scale-Invariant Parameters,” Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI), pp. 4017-4024, 2015. 

J. Zhang and C. Chow, “CRATS: An LDA-Based Model for Jointly Mining Latent Communities, Regions, Activities, Topics, and Sentiments from Geosocial Network Data,” IEEE Transactions on Knowledge and Data Engineering (TKDE 2016), vol. 28, no. 11, pp. 2895–2909, 2016. 

S. Zhao, M. Lyu, and I. King, “STELLAR: Spatial-Temporal Latent Ranking Model for Successive POI Recommendation,” Springer Briefs in Computer Science Point-of-Interest Recommendation in Location-Based Social Networks, pp. 79–94, 2018. 

MovieLens Datasets: collected by GroupLens Research: https://grouplens.org/datasets/movielens/