以循環神經網路為基礎之協同過濾推薦系統｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	胡筱君 Hsiao-Chun Hu
論文名稱：	以循環神經網路為基礎之協同過濾推薦系統 Recurrent Neural Network based Collaborative Filtering Recommender System
指導教授：	吳怡樂 Yi-Leh Wu
口試委員:	閻立剛 Li-Gang Yan 陳建中 Jiann-Jone Chen 唐政元 Cheng-Yuan Tang
學位類別：	碩士 Master
系所名稱：	電資學院 - 資訊工程系 Department of Computer Science and Information Engineering
論文出版年：	2019
畢業學年度：	107
語文別：	英文
論文頁數：	72
中文關鍵詞：	推薦系統、協同式過濾、循環神經網路、隱性評價資料集
外文關鍵詞：	Recommender System, Collaborative Filtering, Recurrent Neural Network, Implicit Feedback Datasets
相關次數：	點閱：263 下載：28
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

隨著電子商務的快速發展，協同式過濾推薦系統已被廣泛地應用於各大網路平台中，利用推薦系統準確預測客戶對商品的偏好，可以解決使用者所面臨的資訊超載問題，並且提高使用者對該網路平台的依賴性。由於以協同式過濾技術為基礎的推薦系統有能力推薦較抽象或難以用文字描述的商品，因此與協同式過濾技術相關的研究越來越受到矚目。本論文結合了深度學習技術，提出一個以循環神經網路為核心的深度學習模型框架，使協同式過濾推薦系統在進行預測時能夠考慮與使用者留下隱性評價記錄的時間相關的因素，進而顯著提升深度學習模型為使用者進行個人化商品推薦的準確性。本論文也提出了一個適用於循環神經網路的訓練資料格式，使我們提出的模型成為第一個能夠同時考慮正面與負面隱性評價訓練資料的循環神經網路模型。此外，透過在 MovieLens-1m 與 Pinterest 這兩個真實世界資料集上進行實驗，我們驗證了相較於目前的深度學習協同式推薦系統，我們所提出的模型能夠更快地完成訓練且有更好的推薦表現。

As the rapid development of e-commerce, Collaborative Filtering Recommender System has been widely applied to major network platforms. Predict customers’ preferences accurately through recommender system could solve the problem of information overload for users and reinforce their dependence on the network platform. Since the recommender system based on collaborative filtering has the ability to recommend products that are abstract or difficult to describe in words, research related to collaborative filtering has attracted more and more attention. In this paper, we propose a deep learning model framework for collaborative filtering recommender system. We use Recurrent Neural Network as the most important part of this framework which makes our model have the ability to consider the timestamp of implicit feedbacks from each user. This ability then significantly improve the performance of our models when making personalization item recommendations. In addition, we also propose a training data format for Recurrent Neural Network. This format makes our recommender system became the first Recurrent Neural Network model that can consider both positive and negative implicit feedback instance during the training process. Through conducted experiments on the two real-world datasets, MovieLens-1m and Pinterest, we verify that our model can finish the training process during a shorter time and have better recommendation performance than the current deep learning based Collaborative Filtering model.

Recommendation Letter ................................................................... i
Approval Letter ................................................................................. ii
Abstract in Chinese .......................................................................... iii
Abstract in English ............................................................................ iv
Acknowledgments ............................................................................ v
Contents ........................................................................................... vi
List of Figures ................................................................................... viii
List of Tables .................................................................................... ix
1 Introduction ................................................................................... 1
1.1 Research Background ................................................................. 1
1.2 Research Motivation ................................................................... 2
1.3 Related Work .............................................................................. 4
1.3.1 Memory-based Collaborative Filtering ...................................... 4
1.3.2 Model-based Collaborative Filtering ......................................... 4
1.3.3 Deep Learning-based Collaborative Filtering .......................... 5
2 Preliminaries .................................................................................. 7
2.1 Recurrent Neural Network ........................................................... 7
2.2 Vanilla RNN ................................................................................. 7
2.3 LongShort-term Memory Network ............................................. 8
2.4 Gated Recurrent Unit ................................................................. 10
3 Proposed Method .......................................................................... 11
3.1 Recurrent Neural Network Based Collaborative Filtering ............ 11
3.2 Input Data Format ....................................................................... 11
3.3 Model Structure .......................................................................... 14
3.4 Dropout Mechanism ................................................................... 16
4 Experiments ................................................................................... 18
4.1 Experimental Settings ................................................................. 18
4.2 The Impact of Input Format(RQ1) ............................................... 23
4.3 The Impact of Dropout Rate(RQ2) .............................................. 25
4.4 The Impact of Deep Learning Factors(RQ3) ............................... 27
4.5 Performance Comparison(RQ4) .................................................. 31
5 Conclusions ................................................................................... 38
References ........................................................................................ 39
Appendix I: More Specific Information Related to RNNCF ................ 41
Appendix II: The Output of Each RNNCF Layer.................................. 49
Letter of Authority ............................................................................. 62
                                

[1] F. Deloche, “A diagram for a one-unit recurrent neural network (rnn).” https://en.wikipedia. org/wiki/File:Recurrent_neural_network_unfold.svg. Accessed November 23, 2018.
[2] F. Deloche, “A diagram for a one-unit long short-term memory (lstm).” https://en.wikipedia. org/wiki/File:Long_Short-Term_Memory.svg. Accessed November 23, 2018.
[3] F. Deloche, “A diagram for a one-unit gated recurrent unit (gru).” https://en.wikipedia.org/ wiki/File:Gated_Recurrent_Unit.svg. Accessed November 23, 2018.
[4] P. Covington, J. Adams, and E. Sargin, “Deep neural networks for youtube recommendations,” in Proceedings of the 10th ACM Conference on Recommender Systems, p. 191–198, ACM, 2016.
[5] A. Germain and J. Chakareski, “Spotify me: Facebook-assisted automatic playlist generation,” in Multimedia Signal Processing (MMSP), 2013 IEEE 15th International Workshop on, p. 025–028, IEEE, 2013.
[6] Z.-D. Zhao and M.-S. Shang, “User-based collaborative-filtering recommendation algorithms on Hadoop,” in Knowledge Discovery and Data Mining, 2010. WKDD’10. Third International Conference on, p. 478–481, IEEE, 2010.
[7] X.Su and T.M.Khoshgoftaar, “A survey of collaborative filtering techniques,” Advances in Artificial Intelligence, vol. 2009, p. 4, 2009.
[8] H. Koohi and K. Kiani, “A new method to find neighbor users that improves the performance of collaborative filtering, ”Expert Systems with Applications, vol. 83, pp. 30–39, 2017.
[9] R. Hu, W. Dou, and J. Liu, “Clubcf: a clustering-based collaborative filtering approach for big data application,” IEEE Transactions on Emerging Topics in Computing, vol. 2, no. 3, pp. 302–313, 2014.
[10] M.Fu, H.Qu, Z.Yi, L.Lu, and Y.Liu, “A novel deep learning-based collaborative filtering model for recommendation system,” IEEE Transactions on Cybernetics, 2018.
[11] X.He, L.Liao, H.Zhang, L.Nie, X.Hu, and T.-S.Chua, “Neural collaborative filtering,” in Proceedings of the 26th International Conference on World Wide Web, pp. 173–182, International World Wide Web Conferences Steering Committee, 2017.
[12] J.L.Elman, “Finding structure in time,” CognitiveScience, vol.14, no.2, pp.179–211, 1990.
[13] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[14] K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using rnn encoder-decoder for statistical machine translation,” in The 2014 Conference on Empirical Methods on Natural Language Processing., SIGDAT, 2014.
[15] Wikipedia,“One-hot encoding.”https://en.wikipedia.org/wiki/One-hot.AccessedNovem- ber 23, 2018.
[16] K.He, X.Zhang, S.Ren, and J.Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778, 2016.
[17] N.Srivastava, G.Hinton, A.Krizhevsky, I.Sutskever, and R.Salakhutdinov,“Dropout: a simple way to prevent neural networks from overfitting,” The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014.
[18] GroupLens,“Movielens 1m dataset.”https://grouplens.org/datasets/movielens/1m/.Ac- cessed November 23, 2018.
[19] G. Xue, “Pinterest iccv dataset.” https://sites.google.com/site/xueatalphabeta/ academic-projects. Accessed November 23, 2018.
[20] Y. Koren, “Factorization meets the neighborhood: a multifaceted collaborative filtering model,” in Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 426–434, ACM, 2008.
[21] X.Geng, H.Zhang, J.Bian, and T.-S.Chua,“Learning image and user features for recommendation in social networks,” in Proceedings of the IEEE International Conference on Computer Vision, pp. 4274– 4282, 2015.
[22] I. Bayer, X. He, B. Kanagal, and S. Rendle, “A generic coordinate descent framework for learning from implicit feedback,” in Proceedings of the 26th International Conference on World Wide Web, pp. 1341–1350, International World Wide Web Conferences Steering Committee, 2017.
[23] X. He, H. Zhang, M.-Y. Kan, and T.-S. Chua, “Fast matrix factorization for online recommendation with implicit feedback,” in Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 549–558, ACM, 2016.
[24] S.Rendle, C.Freudenthaler, Z.Gantner, and L.Schmidt-Thieme,“Bpr: Bayesian personalized ranking from implicit feedback,” in Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, pp. 452–461, AUAI Press, 2009.
[25] A. M. Elkahky, Y. Song, and X. He, “A multi-view deep learning approach for cross-domain user modeling in recommendation systems,” in Proceedings of the 24th International Conference on World Wide Web, pp. 278–288, International World Wide Web Conferences Steering Committee, 2015.
[26] X. He, T. Chen, M.-Y. Kan, and X. Chen, “Trirank: Review-aware explainable recommendation by modeling aspects,” in Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 1661–1670, ACM, 2015.
[27] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in International Conference on Learning Representations (ICLR), Ithaca, 2015.

簡易檢索 / 詳目顯示

相關論文