FedDSE: Distribution-aware Sub-model Extraction for Federated Learning over Resource-constrained Devices-Reference-Cited by-同舟云学术

FedDSE: Distribution-aware Sub-model Extraction for Federated Learning over Resource-constrained Devices

Published:2024-05-13 Issue: Volume: Page:2902-2913
ISSN:
Container-title:Proceedings of the ACM Web Conference 2024
language:
Short-container-title:

Author:

Wang Haozhao¹^ORCID,Jia Yabo²^ORCID,Zhang Meng³^ORCID,Hu Qinghao³^ORCID,Ren Hao⁴^ORCID,Sun Peng⁵^ORCID,Wen Yonggang⁴^ORCID,Zhang Tianwei⁴^ORCID

Affiliation:

1. S-Lab, National Technological University, Singapore, Singapore

2. Zhejiang University, Hangzhou, China

3. S-Lab, Nanyang Technological University, Singapore, Singapore

4. Nanyang Technological University, Singapore, Singapore

5. Sensetime & Shanghai AI Lab, Shanghai, China

Funder

The research is supported under the National Key R\&D Program of China (2022ZD0160201) and the RIE2020 Industry Alignment Fund - Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contributions from the industry partner(s). This work is supported by National Natural Science Foundation of China under grants U1836204, U1936108, 62206102, and Science and Technology Support Program of Hubei Province under grant 2022BAA046 award number(s)

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3589334.3645416

Reference47 articles.

1. Maxwell Mbabilla Aladago and Lorenzo Torresani. [n. d.]. Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks. In38th International Conference on Machine Learning, ICML 2021.

2. Samiul Alam, Luyang Liu, Ming Yan, and Mi Zhang. [n. d.]. FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction. InAdvances in Neural Information Processing Systems 35 (NeurIPS 2022).

3. Sameer Bibikar, Haris Vikalo, Zhangyang Wang, and Xiaohan Chen. [n. d.]. Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better. In36th AAAI Conference on Artificial Intelligence (AAAI 2022).

4. Han Cai, Chuang Gan, Ligeng Zhu, and Song Han. [n. d.]. TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning. InNeurIPS 2020.

5. Sebastian Caldas and Jakub Kone?ný et al. [n. d.]. Expanding the Reach of Federated Learning by Reducing Client Resource Requirements. CoRR 2018 ([n. d.]).

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Is Aggregation the Only Choice? Federated Learning via Layer-wise Model Recombination;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24