請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82077完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳安宇(An-Yeu Wu) | |
| dc.contributor.author | CHEN CHEN | en |
| dc.contributor.author | 陳宸 | zh_TW |
| dc.date.accessioned | 2022-11-25T05:35:22Z | - |
| dc.date.available | 2026-06-30 | |
| dc.date.copyright | 2022-01-03 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-10-27 | |
| dc.identifier.citation | Semiconductor Engineering-AI Chip Architectures Race To The Edge.” https://semiengineering.com/ai-chip-architectures-race-to-the-edge/, Jan. 2019. Accessed: 2021-8-18. 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. O. Gupta and R. Raskar, “Distributed learning of deep neural network over multiple agents,” Journal of Network and Computer Applications, vol. 116, pp. 1–8, 2018. Y. Zhao, M. Li, L. Lai, N. Suda, D. Civin, and V. Chandra, “Federated learning with non-iid data,” arXiv preprint arXiv:1806.00582, 2018. F. Lina, “Deep q network: Combining deep and reinforcement learning.” https://towardsdatascience.com/deep-q-network-combining-deep-reinforcement-learning-a5616bcfc207/, Aug. 2021. Accessed: 2021-8-18. F. Sattler, K.-R. Müller, and W. Samek, “Clustered federated learning: Modelagnostic distributed multitask optimization under privacy constraints,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 8, pp. 3710–3722, 2021. H. Wang, Z. Kaplan, D. Niu, and B. Li, “Optimizing federated learning on non-iid data with reinforcement learning,” in IEEE INFOCOM 2020-IEEE Conference on Computer Communications, pp. 1698–1707, IEEE, 2020. S. B. Kotsiantis, I. D. Zaharakis, and P. E. Pintelas, “Machine learning: a review of classification and combining techniques,” Artificial Intelligence Review, vol. 26, no. 3, pp. 159–190, 2006. H. Wang, C. Ma, and L. Zhou, “A brief review of machine learning and its application,”in 2009 international conference on information engineering and computer science, pp. 1–4, IEEE, 2009. D. Yu and L. Deng, “Deep learning and its applications to signal and information processing [exploratory dsp],” IEEE Signal Processing Magazine, vol. 28, no. 1, pp. 145–154, 2010. R. Collobert and J. Weston, “A unified architecture for natural language processing: Deep neural networks with multitask learning,” in Proceedings of the 25th international conference on Machine learning, pp. 160–167, 2008. S. Ruder, “An overview of gradient descent optimization algorithms,” arXiv preprint arXiv:1609.04747, 2016. W. Y. B. Lim, N. C. Luong, D. T. Hoang, Y. Jiao, Y.-C. Liang, Q. Yang, D. Niyato, and C. Miao, “Federated learning in mobile edge networks: A comprehensive survey,”IEEE Communications Surveys Tutorials, vol. 22, no. 3, pp. 2031–2063, 2020. B. Custers, A. M. Sears, F. Dechesne, I. Georgieva, T. Tani, and S. Van der Hof, EU personal data protection in policy and practice, vol. 29. Springer, 2019. B. M. Gaff, H. E. Sussman, and J. Geetter, “Privacy and big data,” Computer, vol. 47, no. 6, pp. 7–9, 2014. R. Shokri and V. Shmatikov, “Privacy-preserving deep learning,” in Proceedings of the 22nd ACM SIGSAC conference on computer and communications security, pp. 1310–1321, 2015. J. Konečnỳ, H. B. McMahan, D. Ramage, and P. Richtárik, “Federated optimization: Distributed machine learning for on-device intelligence,” arXiv preprint arXiv:1610.02527, 2016. H. Mao, M. Alizadeh, I. Menache, and S. Kandula, “Resource management with deep reinforcement learning,” in Proceedings of the 15th ACM workshop on hot topics in networks, pp. 50–56, 2016. A. Mirhoseini, H. Pham, Q. V. Le, B. Steiner, R. Larsen, Y. Zhou, N. Kumar, M. Norouzi, S. Bengio, and J. Dean, “Device placement optimization with reinforcement learning,” in International Conference on Machine Learning, pp. 2430–2439, PMLR, 2017. M. Zinkevich, M. Weimer, A. J. Smola, and L. Li, “Parallelized stochastic gradient descent.,” in NIPS, vol. 4, p. 4, Citeseer, 2010. A. Agarwal and J. C. Duchi, “Distributed delayed stochastic optimization,” in 2012 IEEE 51st IEEE Conference on Decision and Control (CDC), pp. 5451–5452, IEEE, 2012. R. Mcdonald, M. Mohri, N. Silberman, D. Walker, and G. Mann, “Efficient largescale distributed training of conditional maximum entropy models,” vol. 22, 2009. P. Vepakomma, O. Gupta, T. Swedish, and R. Raskar, “Split learning for health: Distributed deep learning without sharing raw patient data,” arXiv preprint arXiv:1812.00564, 2018. G. J. Annas, “Hipaa regulations —a new era of medical-record privacy?,” 2003. PMID: 12686707. R. B. Ness and f. t. Joint Policy Committee, Societies of Epidemiology, “Influence of the HIPAA Privacy Rule on Health Research,” JAMA, vol. 298, pp. 2164–2170, 11 2007. V. Sharma, P. Vepakomma, T. Swedish, K. Chang, J. Kalpathy-Cramer, and R. Raskar, “Expertmatcher: Automating ml model selection for clients using hidden representations,” arXiv preprint arXiv:1910.03731, 2019. P. Vepakomma, A. Singh, O. Gupta, and R. Raskar, “Nopeek: Information leakage reduction to share activations in distributed deep learning,” in 2020 International Conference on Data Mining Workshops (ICDMW), pp. 933–942, IEEE, 2020. G. J. Székely, M. L. Rizzo, and N. K. Bakirov, “Measuring and testing dependence by correlation of distances,” The annals of statistics, vol. 35, no. 6, pp. 2769–2794, 2007. P. Vepakomma, C. Tonde, and A. Elgammal, “Supervised dimensionality reduction via distance correlation maximization,” Electronic Journal of Statistics, vol. 12, no. 1, pp. 960–984, 2018. Z. Huo, B. Gu, and H. Huang, “Training neural networks using features replay,”arXiv preprint arXiv:1807.04511, 2018. M. Jaderberg, W. M. Czarnecki, S. Osindero, O. Vinyals, A. Graves, D. Silver, and K. Kavukcuoglu, “Decoupled neural interfaces using synthetic gradients,” in International Conference on Machine Learning, pp. 1627–1635, PMLR, 2017. P. Kairouz, H. B. McMahan, B. Avent, A. Bellet, M. Bennis, A. N. Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings, et al., “Advances and open problems in federated learning,” arXiv preprint arXiv:1912.04977, 2019. C. Thapa, M. A. P. Chamikara, and S. Camtepe, “Splitfed: When federated learning meets split learning,” arXiv preprint arXiv:2004.12088, 2020. N. H. Tran, W. Bao, A. Zomaya, M. N. Nguyen, and C. S. Hong, “Federated learning over wireless networks: Optimization model design and analysis,” in IEEE INFOCOM 2019-IEEE Conference on Computer Communications, pp. 1387–1395, IEEE, 2019. S. Wang, T. Tuor, T. Salonidis, K. K. Leung, C. Makaya, T. He, and K. Chan, “Adaptive federated learning in resource constrained edge computing systems,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 6, pp. 1205–1221, 2019. T. Nishio and R. Yonetani, “Client selection for federated learning with heterogeneous resources in mobile edge,” in ICC 2019-2019 IEEE International Conference on Communications (ICC), pp. 1–7, IEEE, 2019. E. Jeong, S. Oh, H. Kim, J. Park, M. Bennis, and S.-L. Kim, “Communicationefficient on-device machine learning: Federated distillation and augmentation under non-iid private data,” arXiv preprint arXiv:1811.11479, 2018. M. Yurochkin, M. Agarwal, S. Ghosh, K. Greenewald, N. Hoang, and Y. Khazaeni,“Bayesian nonparametric federated learning of neural networks,” in International Conference on Machine Learning, pp. 7252–7261, PMLR, 2019. V. Smith, C.-K. Chiang, M. Sanjabi, and A. Talwalkar, “Federated multi-task learning,”arXiv preprint arXiv:1705.10467, 2017. H. Wang, M. Yurochkin, Y. Sun, D. Papailiopoulos, and Y. Khazaeni, “Federated learning with matched averaging,” arXiv preprint arXiv:2002.06440, 2020. S. Caldas, S. M. K. Duddu, P. Wu, T. Li, J. Konečnỳ, H. B. McMahan, V. Smith, and A. Talwalkar, “Leaf: A benchmark for federated settings,” arXiv preprint arXiv:1812.01097, 2018. T. Li, M. Sanjabi, A. Beirami, and V. Smith, “Fair resource allocation in federated learning,” arXiv preprint arXiv:1905.10497, 2019. G. Cohen, S. Afshar, J. Tapson, and A. Van Schaik, “Emnist: Extending mnist to handwritten letters,” in 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2921–2926, IEEE, 2017. Z. Liu, P. Luo, X. Wang, and X. Tang, “Deep learning face attributes in the wild,” in Proceedings of the IEEE international conference on computer vision, pp. 3730–3738, 2015. R. Bellman, “A markovian decision process,” Journal of mathematics and mechanics, vol. 6, no. 5, pp. 679–684, 1957. A. G. Barto, R. S. Sutton, and C. W. Anderson, “Neuronlike adaptive elements that can solve difficult learning control problems,” IEEE transactions on systems, man, and cybernetics, no. 5, pp. 834–846, 1983. R. S. Sutton and A. G. Barto, Reinforcement learning: An introduction. MIT press, 2018. V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing atari with deep reinforcement learning,” arXiv preprint arXiv:1312.5602, 2013. H. Van Hasselt, A. Guez, and D. Silver, “Deep reinforcement learning with double qlearning,”in Proceedings of the AAAI conference on artificial intelligence, vol. 30, 2016. V. François-Lavet, P. Henderson, R. Islam, M. G. Bellemare, and J. Pineau, “An introduction to deep reinforcement learning,” arXiv preprint arXiv:1811.12560, 2018. L.-J. Lin, “Self-improving reactive agents based on reinforcement learning, planning and teaching,” Machine learning, vol. 8, no. 3-4, pp. 293–321, 1992. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. A. E. Eshratifar, M. S. Abrishami, and M. Pedram, “Jointdnn: An efficient training and inference engine for intelligent mobile cloud computing services,” IEEE Transactions on Mobile Computing, 2019. “Performance Ranking of V9 on AnTuTu Benchmark.” https://www.antutu.com/en/ranking/rank1.htm, Aug. 2021. Accessed: 2021-8-18. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82077 | - |
| dc.description.abstract | "邊緣裝置的激增導致用戶數據的數量空前增長。為了避免邊緣端原始資料上傳至雲端的過程中產生隱私疑慮，分布式學習系統能在邊緣端處理這些豐富數據，有望引領下一代智能應用程序和設備的發展。切分學習 (Split Learning) 作為一種很大有前景的分布式學習方法，提供了一種在多個數據存儲庫和運算裝置上訓練單個網絡的拓撲方法。 然而，邊緣裝置生成和收集的數據通常在整個網絡中呈現非獨立同分布(Not Independent and Identically Distributed, non-IID)的狀態，導致了切分學習中的潛在的準確性下降的這一挑戰。針對這個問題，我們提出了使用強化學習做用戶選擇的切分學習(Client Selection in Split Learning with Reinforcement Learning)，它可以在切分學習中進行智慧的用戶選擇從而抵消非獨立同分布數據引入的偏差，並達到與傳統集中式學習演算法相當的準確性。 此外，切分學習系統的固有特徵是要求邊緣端裝置進行依次訓練，這會對系統的速度和效率產生不利影響。在本論文中，通過設置不同數量的集群來控制邊緣端的並行度和模型的整合程度，我們提出了客戶端分群切分學習(Client-clustering Split Learning)，從而在訓練時間和準確性之間進行靈活的權衡。之後，我們又提出了分群數量切換式切分學習(Cluster-switching Split Learning)，通過利用不同集群數量的優勢，只需犧牲少量的模型性能就可以節省大量的訓練時間。 邊緣設備硬體規格的異質性導致了計算能力的多樣性，使得單一方法成為所有情況下的最佳解決方案是不切實際的。因此，在評估了邊緣和服務器之間耗時的不平衡之後，我們分析了適用於各種資源限制場景下的最有效演算法。" | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-25T05:35:22Z (GMT). No. of bitstreams: 1 U0001-2210202116065500.pdf: 7516355 bytes, checksum: af10b58c2b6d3670633d000c0c36317d (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | Acknowledgements vii 摘要 ix Abstract xi Contents xiii List of Figures xvii List of Tables xix Chapter 1 Introduction 1 1.1 Background 1 1.1.1 Deep Learning 1 1.1.2 Issues of Deep Learning 3 1.1.3 Distributed Learning 5 1.2 Challenges and Motivation 7 1.2.1 Challenges of Accuracy Degradation 7 1.2.2 Challenges of Longer Training Time 9 1.3 Thesis Organization 11 Chapter 2 Review of Distributed Learning System 13 2.1 Split Learning (SL) and Related Works 13 2.1.1 Federated Learning (FL) 14 2.1.2 Split Learning (SL) 16 2.1.3 SplitFed Learning (SFL) 20 2.2 Related Works of Client Heterogeneity in Distributed Learning 24 2.2.1 Device Heterogeneity in Distributed Learning 24 2.2.2 Data Heterogeneity in Distributed Learning 25 2.2.3 Client Selection for Dealing with Data Heterogeneity with Reinforcement Learning 26 2.3 Challenges of Prior Works 29 2.4 Verification Benchmark for Distributed settings 30 2.5 Summary 32 Chapter 3 Client Selection in Split Learning with Reinforcement Learning 33 3.1 Necessity of Client Selection in Split Learning 33 3.1.1 The Effect of Non-IID Data on Distributed Learning System 34 3.1.2 Client Selection in Federated Learning 35 3.2 Proposed RL-assisted Split Learning 36 3.2.1 DQN Training 36 3.2.2 DQN Inference 42 3.3 Experimental Results 45 3.3.1 Experimental Settings 45 3.3.2 Experimental Results of RL-assisted Split Learning 50 3.4 Summary 53 Chapter 4 Client-clustering and Cluster-switching Split Learning 55 4.1 Proposed Client-clustering Split Learning System 55 4.1.1 The Influence of Sequential Training 56 4.1.2 Algorithm Design 57 4.2 Details of Time Measurement 61 4.3 Proposed Cluster-switching Split Learning 62 4.4 Experimental Results 65 4.4.1 Experimental Results of Client-clustering Split Learning System 65 4.4.2 Experimental Results of Cluster-switching Split Learning System 69 4.5 Summary 70 Chapter 5 Resource Constrained Split Learning System 71 5.1 Issue of Device Heterogeneity 71 5.2 Training Time Analysis 73 5.3 Simulation Results 74 5.3.1 Experimental Settings 75 5.3.2 Experimental Results 76 5.4 Summary 79 Chapter 6 Conclusion 81 6.1 Main Contributions 81 6.2 Future Directions 82 References 85 | |
| dc.language.iso | en | |
| dc.subject | 資源限制 | zh_TW |
| dc.subject | 分群 | zh_TW |
| dc.subject | 分布式學習 | zh_TW |
| dc.subject | 切分學習 | zh_TW |
| dc.subject | 强化學習 | zh_TW |
| dc.subject | 非獨立同分布 | zh_TW |
| dc.subject | Split Learning | en |
| dc.subject | Resource-constrained | en |
| dc.subject | Clustering | en |
| dc.subject | Non-IID | en |
| dc.subject | Reinforcement Learning | en |
| dc.subject | Distributed Learning | en |
| dc.title | 適用於非獨立同分布用戶之有效分群式切分學習系統 | zh_TW |
| dc.title | Efficient Cluster-based Split Learning System for Non-IID Clients | en |
| dc.date.schoolyear | 110-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 蔡佩芸(Hsin-Tsai Liu),施吉昇(Chih-Yang Tseng),楊佳玲 | |
| dc.subject.keyword | 分布式學習,切分學習,强化學習,非獨立同分布,分群,資源限制, | zh_TW |
| dc.subject.keyword | Distributed Learning,Split Learning,Reinforcement Learning,Non-IID,Clustering,Resource-constrained, | en |
| dc.relation.page | 91 | |
| dc.identifier.doi | 10.6342/NTU202104038 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-10-28 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2026-06-30 | - |
| 顯示於系所單位： | 電子工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2210202116065500.pdf 未授權公開取用 | 7.34 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。