請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88361完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳家麟 | zh_TW |
| dc.contributor.advisor | Ja-Ling Wu | en |
| dc.contributor.author | 阮品紘 | zh_TW |
| dc.contributor.author | Pin-Hung Juan | en |
| dc.date.accessioned | 2023-08-09T16:43:21Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-09 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-07-26 | - |
| dc.identifier.citation | [1] Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR, 2017.
[2] Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. Branchynet: Fast inference via early exiting from deep neural networks. In 2016 23rd International Conference on Pattern Recognition (ICPR), pages 2464–2469. IEEE, 2016. [3] Ting-Kuei Hu, Tianlong Chen, Haotao Wang, and Zhangyang Wang. Triple wins: Boosting accuracy, robustness and efficiency together by enabling input-adaptiveinference. arXiv preprint arXiv:2002.10025, 2020. [4] Wei Yang Bryan Lim, Nguyen Cong Luong, Dinh Thai Hoang, Yutao Jiao, Ying-Chang Liang, Qiang Yang, Dusit Niyato, and Chunyan Miao. Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 22(3):2031–2063, 2020. [5] Syreen Banabilah, Moayad Aloqaily, Eitaa Alsayed, Nida Malik, and Yaser Jararweh. Federated learning review: Fundamentals, enabling technologies, and future applications. Information processing & management, 59(6):103061, 2022. [6] Tuo Zhang, Lei Gao, Chaoyang He, Mi Zhang, Bhaskar Krishnamachari, and A Salman Avestimehr. Federated learning for the internet of things: applications, challenges, and opportunities. IEEE Internet of Things Magazine, 5(1):24–29, 2022. [7] Rodolfo Stoffel Antunes, Cristiano André da Costa, Arne Küderle, Imrana Abdullahi Yari, and Björn Eskofier. Federated learning for healthcare: Systematic review and architecture proposal. ACM Transactions on Intelligent Systems and Technology(TIST), 13(4):1–23, 2022. [8] Linlin Tu, Xiaomin Ouyang, Jiayu Zhou, Yuze He, and Guoliang Xing. Feddl: Federated learning via dynamic layer sharing for human activity recognition. In Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems, pages 15–28, 2021. [9] Qiong Wu, Kaiwen He, and Xu Chen. Personalized federated learning for intelligent iot applications: A cloud-edge based framework. IEEE Open Journal of the Computer Society, 1:35–44, 2020. [10] Peter Kairouz, H Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al. Advances and open problems in federated learning. Foundations and Trends® in Machine Learning, 14(1–2):1–210, 2021. [11] Ching-Hao Wang, Kang-Yang Huang, Jun-Cheng Chen, Hong-Han Shuai, and Wen- Huang Cheng. Heterogeneous federated learning through multi-branch network. In 2021 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE, 2021. [12] Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems, 2:429–450, 2020. [13] Sashank Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Konečnỳ, Sanjiv Kumar, and H Brendan McMahan. Adaptive federated optimization. arXiv preprint arXiv:2003.00295, 2020. [14] Kaiju Li, Hao Wang, and Qinghua Zhang. Fedtcr: communication-efficient federated learning via taming computing resources. Complex & Intelligent Systems, pages 1–21, 2023. [15] Hong Huang, Lan Zhang, Chaoyue Sun, Ruogu Fang, Xiaoyong Yuan, and Dapeng Wu. Fedtiny: Pruned federated learning towards specialized tiny models. arXiv preprint arXiv:2212.01977, 2022. [16] Tao Lin, Lingjing Kong, Sebastian U Stich, and Martin Jaggi. Ensemble distillation for robust model fusion in federated learning. Advances in Neural Information Processing Systems, 33:2351–2363, 2020. [17] Fan Lai, Xiangfeng Zhu, Harsha V Madhyastha, and Mosharaf Chowdhury. Oort:Efficient federated learning via guided participant selection. In OSDI, pages 19–35,2021. [18] Daliang Li and Junpu Wang. Fedmd: Heterogenous federated learning via model distillation. arXiv preprint arXiv:1910.03581, 2019. [19] Fan Lai, Yinwei Dai, Sanjay Singapuram, Jiachen Liu, Xiangfeng Zhu, Harsha Mad-hyastha, and Mosharaf Chowdhury. Fedscale: Benchmarking model and system performance of federated learning at scale. In International Conference on Machine Learning, pages 11814–11827. PMLR, 2022. [20] Alex Krizhevsky. Learning multiple layers of features from tiny images. PhD thesis,University of Toronto, 2009. [21] Gregory Cohen, Saeed Afshar, Jonathan Tapson, and André van Schaik. EMNIST: an extension of MNIST to handwritten letters. In arxiv.org/abs/1702.05373, 2017. [22] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88361 | - |
| dc.description.abstract | 在本研究中，我們提出了一種聯邦學習的方法，將多分支網路與Oort客戶端選擇算法結合，以提高聯邦學習系統的性能。該方法成功地解決了非獨立同分布（non-iid）數據的重要問題，這是MFedAvg方法尚未充分解決的挑戰。此外，本研究的一項關鍵創新是引入了一種名為"均勻性"的度量，用以量化聯邦學習環境中參與者之間訓練時間的差異。這一新概念不僅有助於識別落後者，而且為評估系統的公平性和效率提供了值得參考的見解。實驗結果強調了將多分支網路與oort客戶端選擇算法集成的優點，並凸顯了在設計和評估聯邦學習系統中，"均勻性"的關鍵作用。 | zh_TW |
| dc.description.abstract | In this study, we present a federated learning approach that combines a multi-branch network and the Oort client selection algorithm to improve the performance of federated learning systems. This method successfully addresses the significant issue of non-iid data, a challenge not adequately tackled by the MFedAvg method. Additionally, one of the key innovations of this research is the introduction of uniformity, a metric that quantifies the disparity in training time amongst participants in a federated learning setup. This novel concept not only aids in identifying stragglers but also provides valuable insights into the assessing fairness and efficiency of the system. Experimental results underscore the merits of the integrated multi-branch network with the Oort client selection algorithm and highlight the crucial role of uniformity in designing and evaluating federated learning systems. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-09T16:43:21Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-09T16:43:21Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee . . . . . . . . . . . i
Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii 摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii Chapter 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 Chapter 2 Preliminary . . . . . . . . . . . . . . . . . . . . . . . . . . . .3 2.1 Federated Learning . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.2 Multi-Branch Networks . . . . . . . . . . . . . . . . . . . . . . . .4 Chapter 3 Related Works . . . . . . . . . . . . . . . . . . . . . . . . . . .6 3.1 Homogeneous Model FL . . . . . . . . . . . . . . . . . . . . . . . . 7 3.2 Heterogeneous Model FL . . . . . . . . . . . . . . . . . . . . . . . 8 3.3 Oort - clients selection for FL . . . . . . . . . . . . . . . . . . .9 Chapter 4 Proposed Method . . . . . . . . . . . . . . . . . . . . . . . . . .11 4.1 Construct a Multi-Branch Network . . . . . . . . . . . . . . . . . . 12 4.2 model Distributor . . . . . . . . . . . . . . . . . . . . . . . . . .13 4.3 Overall System Architecture . . . . . . . . . . . . . . . . . . . . .14 Chapter 5 Experiments . . . . . . . . . . . . . . . . . . . . .. . . . . . . 17 5.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . 17 5.1.1 Environment Setting . . . . . . . . . . . . . . . . . . . . . .17 5.1.2 Model Setting . . . . . . . . . . . . . . . . . . . . . . . . .18 5.2 Training Details . . . . . . . . . . . . . . . . . . . . . . . . . . 18 5.3 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . 19 5.3.1 Time-to-accuracy Performance . . . . . . . . . . . . . . . . . 19 5.3.2 Rounds-to-accuracy Performance . . . . . . . . . . . . . . . . 20 5.3.3 Uniformity . . . . . . . . . . . . . . . . . . . . . . . . . . 22 5.4 Ablation Studies . . . . . . . . . . . . . . . . . . . . . . . . . . 24 5.4.1 Integration with other methods . . . . . . . . . . . . . . . . 24 5.4.2 The Effects of Different communication bandwidth ratios (μ) . .25 Chapter 6 Conclusion . . . . . . . . . . . . . . . . . . . . .. . . . . . . .27 References . . . . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . .29 | - |
| dc.language.iso | en | - |
| dc.subject | 聯邦學習 | zh_TW |
| dc.subject | 通訊高效 | zh_TW |
| dc.subject | 訓練時間均勻度 | zh_TW |
| dc.subject | 客戶選擇 | zh_TW |
| dc.subject | 多分支網路 | zh_TW |
| dc.subject | Training Time Uniformity | en |
| dc.subject | Communication-efficient | en |
| dc.subject | Client selection | en |
| dc.subject | Federated Learning | en |
| dc.subject | Multi-Branch Network | en |
| dc.title | 透過多分支網路增強聯邦學習的通訊效率和訓練時間均勻性 | zh_TW |
| dc.title | Enhancing Communication efficiency and Training time uniformity in Federated Learning through Multi-Branch Networks | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳文進;許超雲 | zh_TW |
| dc.contributor.oralexamcommittee | Wen-Chin Chen;Chau-Yun Hsu | en |
| dc.subject.keyword | 聯邦學習,訓練時間均勻度,通訊高效,客戶選擇,多分支網路, | zh_TW |
| dc.subject.keyword | Federated Learning,Training Time Uniformity,Communication-efficient,Client selection,Multi-Branch Network, | en |
| dc.relation.page | 32 | - |
| dc.identifier.doi | 10.6342/NTU202301364 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2023-07-27 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 7.63 MB | Adobe PDF |
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。