ChronusFed: Reinforcement-Based Adaptive Partial Training for Heterogeneous Federated Learning
Authors: 
Fuyuan Xia, Chenhao Ying, David S.L. Wei, Wei Chen, Weiting Zhang, Haiming Jin, Yuan LuoAuthors Info & Claims
Pages 464 - 473
Abstract
Due to the progress in computer hardware and network technologies, federated learning (FL), a decentralized training method in machine learning, has garnered widespread attention. In this approach, individuals share local model parameters rather than raw training data to protect their privacy. However, the inherent heterogeneity of practical computing devices poses challenges to the efficiency and performance of FL. In this paper, we explore the landscape of heterogeneous FL frameworks and introduce ChronusFed, a reinforCement-based adaptive partial training method for heterogeneous Federated learning. ChronusFed employs a dynamic epoch adjustment mechanism (DEA) and a customizable partial training framework (CPT) to optimize model training efficiency. By integrating DEA and CPT, ChronusFed effectively tackles the straggler issues that arise from limited hardware resources, while simultaneously enhancing the model performance. More specifically, DEA leverages deep reinforcement learning (DRL) to model the current state of the global model and determine optimal local training epochs, while CPT utilizes our proposed maximum coverage algorithm to handle device heterogeneity and accelerate model convergence. Theoretical analysis of training convergence validates the effectiveness of ChronusFed, and comprehensive experimental evaluations demonstrate that ChronusFed outperforms state-of-the-art methods across various learning tasks, showcasing its robustness and superiority in heterogeneous FL scenarios.
References
[1]
Samiul Alam, Luyang Liu, Ming Yan, and Mi Zhang. 2022. Fedrolex: Model-heterogeneous federated learning with rolling sub-model extraction. Advances in neural information processing systems 35 (2022), 29677–29690.
[2]
Sofiane Bouaziz, Hadjer Benmeziane, Youcef Imine, Leila Hamdad, Smail Niar, and Hamza Ouarnoughi. 2023. FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learning. In 2023 IEEE 41st International Conference on Computer Design (ICCD). IEEE, 444–447.
[3]
Chunjiang Che, Xiaoli Li, Chuan Chen, Xiaoyu He, and Zibin Zheng. 2022. A decentralized federated learning framework via committee mechanism with convergence guarantee. IEEE Transactions on Parallel and Distributed Systems 33, 12 (2022), 4783–4800.
[4]
Yae Jee Cho, Andre Manoel, Gauri Joshi, Robert Sim, and Dimitrios Dimitriadis. 2022. Heterogeneous ensemble knowledge transfer for training large models in federated learning. arXiv preprint arXiv:2204.12703 (2022).
[5]
Patryk Chrabaszcz, Ilya Loshchilov, and Frank Hutter. 2017. A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv preprint arXiv:1707.08819 (2017).
[6]
Yangguang Cui, Zhixing Zhang, Nuo Wang, Liying Li, Chunwei Chang, and Tongquan Wei. 2023. User-Distribution-Aware Federated Learning for Efficient Communication and Fast Inference. IEEE Trans. Comput. (2023).
[7]
Ringki Das and Thoudam Doren Singh. 2023. Multimodal sentiment analysis: A survey of methods, trends and challenges. Comput. Surveys (2023).
[8]
Enmao Diao, Jie Ding, and Vahid Tarokh. 2021. HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients. In 9th International Conference on Learning Representations, ICLR 2021.
[9]
Di Feng, Christian Haase-Schütz, Lars Rosenbaum, Heinz Hertlein, Claudius Gläser, Fabian Timm, Werner Wiesbeck, and Klaus Dietmayer. 2021. Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges. IEEE Transactions on Intelligent Transportation Systems 22, 3 (2021), 1341–1360.
[10]
Samuel Horvath, Stefanos Laskaridis, Mario Almeida, Ilias Leontiadis, Stylianos Venieris, and Nicholas Lane. 2021. Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout. Advances in Neural Information Processing Systems 34 (2021), 12876–12889.
[11]
Chung-Hsuan Hu, Zheng Chen, and Erik G Larsson. 2023. Scheduling and aggregation design for asynchronous federated learning over wireless networks. IEEE Journal on Selected Areas in Communications 41, 4 (2023), 874–886.
[12]
Zhida Jiang, Yang Xu, Hongli Xu, Zhiyuan Wang, Chunming Qiao, and Yangming Zhao. 2022. Fedmp: Federated learning through adaptive model pruning in heterogeneous edge computing. In 2022 IEEE 38th International Conference on Data Engineering (ICDE). IEEE, 767–779.
[13]
Alex Krizhevsky, Geoffrey Hinton, 2009. Learning multiple layers of features from tiny images. (2009).
[14]
Guanghao Li, Yue Hu, Miao Zhang, Ji Liu, Quanjun Yin, Yong Peng, and Dejing Dou. 2022. FedHiSyn: A hierarchical synchronous federated learning framework for resource and data heterogeneity. In Proceedings of the 51st International Conference on Parallel Processing. 1–11.
[15]
Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems 2 (2020), 429–450.
[16]
Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang. 2019. On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189 (2019).
[17]
Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR.
[18]
Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, and Jan Kautz. 2016. Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016).
[19]
Nang Hung Nguyen, Phi Le Nguyen, Thuy Dung Nguyen, Trung Thanh Nguyen, Duc Long Nguyen, Thanh Hung Nguyen, Huy Hieu Pham, and Thao Nguyen Truong. 2022. FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learning. In Proceedings of the 51st International Conference on Parallel Processing. 1–11.
[20]
Mehdi Setayesh, Xiaoxiao Li, and Vincent WS Wong. 2022. PerFedMask: Personalized Federated Learning with Optimized Masking Vectors. In The Eleventh International Conference on Learning Representations.
[21]
Xiaoli Tang and Han Yu. 2023. Competitive-cooperative multi-agent reinforcement learning for auction-based federated learning. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. 4262–4270.
[22]
Hao Wang, Zakhary Kaplan, Di Niu, and Baochun Li. 2020. Optimizing federated learning on non-iid data with reinforcement learning. In IEEE INFOCOM 2020-IEEE Conference on Computer Communications. IEEE, 1698–1707.
[23]
Yansheng Wang, Yongxin Tong, Zimu Zhou, Ruisheng Zhang, Sinno Jialin Pan, Lixin Fan, and Qiang Yang. 2023. Distribution-Regularized Federated Learning on Non-IID Data. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 2113–2125.
[24]
Bibo Wu, Fang Fang, and Xianbin Wang. 2023. Joint age-based client selection and resource allocation for communication-efficient federated learning over noma networks. IEEE Transactions on Communications (2023).
[25]
Tianao Xiang, Yuanguo Bi, Xiangyi Chen, Yuan Liu, Boyang Wang, Xuemin Shen, and Xingwei Wang. 2023. Federated Learning with Dynamic Epoch Adjustment and Collaborative Training in Mobile Edge Computing. IEEE Transactions on Mobile Computing (2023).
[26]
Ling Yang, Zhilong Zhang, Yang Song, Shenda Hong, Runsheng Xu, Yue Zhao, Wentao Zhang, Bin Cui, and Ming-Hsuan Yang. 2022. Diffusion models: A comprehensive survey of methods and applications. Comput. Surveys (2022).
[27]
Dezhong Yao, Wanning Pan, Yutong Dai, Yao Wan, Xiaofeng Ding, Chen Yu, Hai Jin, Zheng Xu, and Lichao Sun. 2023. FedGKD: Towards Heterogeneous Federated Learning via Global Knowledge Distillation. IEEE Trans. Comput. (2023).
[28]
Hao Yu, Sen Yang, and Shenghuo Zhu. 2019. Parallel restarted SGD with faster convergence and less communication: Demystifying why model averaging works for deep learning. In Proceedings of the AAAI conference on artificial intelligence.
[29]
Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Jian Cao, and Haibing Guan. 2023. Gpfl: Simultaneously learning global and personalized feature information for personalized federated learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5041–5051.
[30]
Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, and Haibing Guan. 2023. Fedala: Adaptive local aggregation for personalized federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence.
[31]
Sai Qian Zhang, Jieyu Lin, and Qi Zhang. 2022. A multi-agent reinforcement learning approach for efficient client selection in federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 9091–9099.
Index Terms
- ChronusFed: Reinforcement-Based Adaptive Partial Training for Heterogeneous Federated Learning
Recommendations
Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
AbstractFederated learning (FL) is a promising approach that enables distributed clients to collaboratively train a global model while preserving their data privacy. However, FL often suffers from data heterogeneity problems, which can significantly ...
Adaptive device sampling and deadline determination for cloud-based heterogeneous federated learning
AbstractAs a new approach to machine learning, Federated learning enables distributned traiing on edge devices and aggregates local models into a global model. The edge devices that participate in federated learning are highly heterogeneous in terms of ...
Towards federated unsupervised representation learning
EdgeSys '20: Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and NetworkingMaking deep learning models efficient at inferring nowadays requires training with an extensive number of labeled data that are gathered in a centralized system. However, gathering labeled data is an expensive and time-consuming process, centralized ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
August 2024
1279 pages
ISBN:9798400717932
DOI:10.1145/3673038
Copyright © 2024 Owner/Author.
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 12 August 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICPP '24
ICPP '24: the 53rd International Conference on Parallel Processing
August 12 - 15, 2024
Gotland, Sweden
Acceptance Rates
Overall Acceptance Rate 91 of 313 submissions, 29%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 154Total Downloads
- Downloads (Last 12 months)154
- Downloads (Last 6 weeks)50
Reflects downloads up to 16 Nov 2024
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in