多媒體內容推薦與根據多任務聯邦學習之推薦結果進行內容緩存

簡易檢索 / 詳目顯示

回結果列表

研究生：	許書容 Hsu, Shu-Jung
論文名稱：	多媒體內容推薦與根據多任務聯邦學習之推薦結果進行內容緩存 Multimedia Content Recommendation and Caching by Multi-Task Federated Learning
指導教授：	洪樂文 Hong, Yao-Win Peter
口試委員:	楊明勳 Yang, Ming-Hsun 劉光浩 Liu, Kuang-Hao
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 通訊工程研究所 Communications Engineering
論文出版年：	2023
畢業學年度：	111
語文別：	英文
論文頁數：	34
中文關鍵詞：	協同過濾、神經網絡、聯邦多任務學習、文件熱門程度預測
外文關鍵詞：	collaborative filtering, neural networks, federated multitask learning, file popularity prediction
相關次數：	點閱：3 下載：0
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

此研究是關於多媒體內容推薦及其在緩存策略中的應用。首先我們根據使用者對電影預告片的反應來預測偏好。我們通過一個影片平台收集使用者評分以及面部表情，再將使用者的面部表情量化為情感標籤，最後提出一個基於多任務學習的模型，同時訓練主要評分任務和輔助情感任務。實驗結果證實多任務模型的性能優於單任務模型。接著，考慮到現實中影片文件緩存在周邊的基地台或者邊緣伺服器中，由於緩存器的容量有限，需要預測本地的文件熱門程度來決定緩存哪些文件，所以我們開發基於推薦系統的緩存策略。由於使用者群體的不同偏好導致的異質性，我們考慮多任務聯邦學習場景。我們通過聯邦學習確保隱私，並使用基於專家的模型，該模型可以自動調整參數權重以處理不同的本地任務並減輕任務之間的干擾。實驗結果證明使用推薦系統預測文件熱門程度可以提高緩存效率。

This work is about the multimedia content recommendation and its application in caching strategy. First, we predict preferences based on users' reactions to movie trailers. We collect user ratings and facial expressions through a video platform, quantify users' facial expressions into emotion labels, and finally propose a model based on multi-task learning to simultaneously train the main rating task and the auxiliary emotion task. Experimental results confirm that the performance of multi-task model is better than that of single-task model. Next, considering that video files are cached in surrounding base stations or edge servers in reality, due to the limited capacity of caching entities, we need to predict the file popularity of the local to decide which files to cache, so we develop a caching strategy based on a recommendation system. Due to the heterogeneity caused by the different preferences of user groups, we consider a multi-task federated learning scenario. We ensure privacy through federated learning and use an expert-based model that can automatically adjust parameter weights to handle different local tasks and mitigate interference between tasks. The simulations show that using recommendation system to predict file popularity can improve caching efficiency.

Abstract i
Contents ii
Introduction 1
Background and Related Works 5
1 Recommendation System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1.1 Conventional method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1.2 NN-based Recommendation System . . . . . . . . . . . . . . . . . . . . . 6
2 Distributed learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.1 General Distributed learning . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2 Distributed Recommendation System . . . . . . . . . . . . . . . . . . . . 7
3 File Popularity Prediction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Multimedia Content Recommendation 10
1 Data Collection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
1.1 Data Collection Procedure . . . . . . . . . . . . . . . . . . . . . . . . . . 11
1.2 Platform . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2 Database Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.1 User Rating . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.2 Emotion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.3 Emotion vs. User Rating . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3 Multi-task Recommendation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
4 Experimental Results on Multi-Task Recommendation . . . . . . . . . . . . . . . 15
Caching by Multi-Task Federated Learning 16
1 System Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
2 Proposed Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
3 Federated Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
3.1 Local Training . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.2 Aggregation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
4 Caching Policy: Predict File Popularity . . . . . . . . . . . . . . . . . . . . . . . 19
Experimental Results 21
1 Dataset Description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
2 Evaluation Protocols . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
3 Baseline Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4 Parameter Settings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
5 Dataset Configuration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
6 Experiment Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
Conclusion 30
Bibliography 31
                                

[1] Y. Koren, R. Bell, and C. Volinsky, “Matrix factorization techniques for recommender systems,” Computer, vol. 42, no. 8, pp. 30–37, 2009.
[2] X.Wang, X. He, M.Wang, F. Feng, and T.-S. Chua, “Neural graph collaborative filtering,” in Proceedings of the 42nd international ACM SIGIR conference on Research and development in Information Retrieval, pp. 165–174, 2019.
[3] X. He, X. Du, X. Wang, F. Tian, J. Tang, and T.-S. Chua, “Outer product-based neural collaborative filtering,” arXiv preprint arXiv:1808.03912, 2018.
[4] H.-J. Xue, X. Dai, J. Zhang, S. Huang, and J. Chen, “Deep matrix factorization models for recommender systems.,” in IJCAI, vol. 17, pp. 3203–3209, Melbourne, Australia, 2017.
[5] S. Zhang, L. Yao, A. Sun, and Y. Tay, “Deep learning based recommender system: A survey and new perspectives,” ACM Computing Surveys (CSUR), vol. 52, no. 1, pp. 1–38, 2019.
[6] 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, 2017.
[7] H.-T. Cheng, L. Koc, J. Harmsen, T. Shaked, T. Chandra, H. Aradhye, G. Anderson, G. Corrado, W. Chai, M. Ispir, et al., “Wide & deep learning for recommender systems,” in Proceedings of the 1st workshop on deep learning for recommender systems, pp. 7–10, 2016.
[8] C. Gao, X. He, D. Gan, X. Chen, F. Feng, Y. Li, T.-S. Chua, and D. Jin, “Neural multi-task recommendation from multi-behavior data,” in 2019 IEEE 35th international conference on data engineering (ICDE), pp. 1554–1557, IEEE, 2019.
[9] X. Ma, L. Zhao, G. Huang, Z. Wang, Z. Hu, X. Zhu, and K. Gai, “Entire space multitask model: An effective approach for estimating post-click conversion rate,” in The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 1137–1140, 2018.
[10] Z. Yu, J. Hu, G. Min, H. Lu, Z. Zhao, H. Wang, and N. Georgalas, “Federated learning based proactive content caching in edge computing,” in 2018 IEEE Global Communications Conference (GLOBECOM), pp. 1–6, IEEE, 2018.
[11] K. Qi and C. Yang, “Popularity prediction with federated learning for proactive caching at wireless edge,” in 2020 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1–6, IEEE, 2020.
[12] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial intelligence and statistics, pp. 1273–1282, PMLR, 2017.
[13] J. Ma, Z. Zhao, X. Yi, J. Chen, L. Hong, and E. H. Chi, “Modeling task relationships in multitask learning with multi-gate mixture-of-experts,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1930–1939, 2018.
[14] Z. Zhao, L. Hong, L. Wei, J. Chen, A. Nath, S. Andrews, A. Kumthekar, M. Sathiamoorthy, X. Yi, and E. Chi, “Recommending what video to watch next: a multitask ranking system,” in Proceedings of the 13th ACM Conference on Recommender Systems, pp. 43–51, 2019.
[15] H. Tang, J. Liu, M. Zhao, and X. Gong, “Progressive layered extraction (ple): A novel multitask learning (mtl) model for personalized recommendations,” in Fourteenth ACM Conference on Recommender Systems, pp. 269–278, 2020.
[16] J. Koneˇcn`y, H. B. McMahan, F. X. Yu, P. Richtárik, A. T. Suresh, and D. Bacon, “Federated learning: Strategies for improving communication efficiency,” arXiv preprint arXiv:1610.05492, 2016.
[17] V. Smith, C.-K. Chiang, M. Sanjabi, and A. S. Talwalkar, “Federated multi-task learning,” Advances in neural information processing systems, vol. 30, 2017.
[18] M. Ammad-Ud-Din, E. Ivannikova, S. A. Khan,W. Oyomno, Q. Fu, K. E. Tan, and A. Flanagan, “Federated collaborative filtering for privacy-preserving personalized recommendation system,” arXiv preprint arXiv:1901.09888, 2019.
[19] K. Muhammad, Q. Wang, D. O’Reilly-Morgan, E. Tragos, B. Smyth, N. Hurley, J. Geraci, and A. Lawlor, “Fedfast: Going beyond average for faster training of federated recommender systems,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1234–1242, 2020.
[20] Y. Wu, Y. Jiang, M. Bennis, F. Zheng, X. Gao, and X. You, “Content popularity prediction in fog radio access networks: A federated learning based approach,” in ICC 2020-2020 IEEE International Conference on Communications (ICC), pp. 1–6, IEEE, 2020.
[21] H.-T. Chang and Y.-W. P. Hong, “Crowdsourcing of reactors’ labeled multimedia contents and pairwise comparison rank aggregation,” National Tsing Hua University(NTHU), 2021. https://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o= dnclcdr&s=id=%22109NTHU5650070%22.&searchmode=basic.
[22] T. Baltrusaitis, A. Zadeh, Y. C. Lim, and L.-P. Morency, “Openface 2.0: Facial behavior analysis toolkit,” in 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018), pp. 59–66, IEEE, 2018.
[23] R. Ekman, What the face reveals: Basic and applied studies of spontaneous expression using the Facial Action Coding System (FACS). Oxford University Press, USA, 1997.
[24] F. M. Harper and J. A. Konstan, “The movielens datasets: History and context,” Acm transactions on interactive intelligent systems (tiis), vol. 5, no. 4, pp. 1–19, 2015.
[25] B. M. Marlin, “Modeling user rating profiles for collaborative filtering,” Advances in neural information processing systems, vol. 16, 2003.

簡易檢索 / 詳目顯示

相關論文