PDF (3.9 MB)
Collect
Submit Manuscript
Open Access

ResFed: An Accurate and Light Federated Multi-Shot Pre-Trained Model on Edge Devices

Department of Computer Engineering, ‎Bu-Ali Sina University, Hamedan 6516738695, Iran
Department of ‎Electrical Engineering, Bu-Ali Sina University, ‎Hamedan 6516738695, Iran
Department of Informatics, University of Oslo, Oslo NO-0316, Norway
Laboratory for Protected Horticulture, Weifang ‎University of Science and Technology, ‎Weifang 262700, China
Show Author Information

Abstract

The rise of machine learning applications at the network edge demands real-time prediction with limited resources, requiring low computational complexity and accurate models. Also, these devices may have poor learning ability due to the lack of samples. Using federated learning enables devices to train machine learning models without sharing their private data. Meta-learning algorithms, particularly few-shot learning, are ideal for federated environments with highly personalized and decentralized training data due to their fast adaptation and good generalization to new tasks. ‎ Despite recent advances, the use of metric-based meta-learning methods remains ambiguous due to ‎their simplicity, as well as their development to improve model learning ability and accuracy in a federated ‎environment. This paper introduces ResFed, a federated meta-learning method specifically tailored for few-shot ‎classification. The approach involves leveraging a pre-trained model and implementing data augmentation within the federated meta-learner, leading to favorable performance outcomes. The experimental results show that our approach, specifically designed for limited data scenarios in the federated environments, significantly improves convergence speed and accuracy. The values of accuracy obtained in CIFAR-100 and Omniglot ‎datasets are 77.44% and 98.24%, respectively. Additionally, when compared to alternative methods, there is a notable reduction in resource costs ranging from 0.4 to 0.61 in diverse scenarios.

References

[1]
A. Souri, A. Hussien, M. Hoseyninezhad, and M. Norouzi, A systematic review of IoT communication strategies for an efficient smart ‎environment, Trans. Emerg. Telecommun. Technol., vol. 33, no. 3, p. e3736, 2022. ‎
[2]
‎P. Hosseinioun, M. Kheirabadi, S. R. K. Tabbakh, and R. Ghaemi, A new energy-aware tasks scheduling approach in fog computing using hybrid ‎meta-heuristic algorithm, J. Parallel Distrib. Comput., vol. 143, pp. 88–96, 2020. ‎
[3]
‎ Cisco, Cisco Annual Internet Report (2018–2023 ) White Paper. San Jose, CA, USA: Cisco, 2020. ‎
[4]
M. Asad, A. Moustafa, and T. Ito, Federated learning versus classical machine learning: A ‎convergence comparison, arXiv preprint arXiv: 2107.10976, 2021. ‎
[5]
P. Li, J. Li, Z. Huang, T. Li, C. Z. Gao, S. M. Yiu, and K. Chen, Multi-key privacy-preserving deep learning in cloud computing, Future Gener. ‎Comput. ‎Syst., vol. 74, pp. 76–85, 2017. ‎
[6]
B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. Agüera y Arcas, Communication-efficient learning of deep networks from decentralized data, in Proc. 20 th Int. Conf. ArtificialIntelligence and Statistics, Fort Lauderdale, FL, USA, 2017, pp. 1273–1282. ‎
[7]
‎ N. A. Jalali and H. Chen, Federated learning security and privacy-preserving algorithm and ‎experiments research under internet of things critical infrastructure, Tsinghua Science and Technology, vol. 29, no. 2, pp. 400–414, 2024. ‎
[8]
W. Zhang, Z. Li, and X. Chen, Quality-aware user recruitment based on federated learning in mobile crowd ‎sensing, Tsinghua Science and Technology., vol. 26, no. 6, pp. 869–877, 2021. ‎
[9]
J. Konečný, 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, 2017. ‎
[10]
D. Chen, Y. C. Liu, B. Kim, J. Xie, C. S. Hong, and Z. Han, Edge computing resources reservation in vehicular networks: A meta-learning ‎approach, IEEE Trans. Veh. Technol., vol. 69, no. 5, pp. 5634–5646, 2020. ‎
[11]
C. Zhao, X. Sun, S. Yang, X. Ren, P. Zhao, and J. McCann, Exploration across small silos: Federated few-shot learning on network edge, IEEENetw., vol. 36, no. 1, pp. 159–165, 2022. ‎
[12]
O. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, and D. Wierstra, Matching networks for one shot learning, in Proc. 30 th Int. Conf. Neural InformationProcessing Systems, Barcelona, Spain, 2016, pp. 3637–3645. ‎
[13]
Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, Generalizing from a few examples: A survey on few-shot learning, ACM Comput. ‎Surveys, vol. 53, no. 3, p. 63, 2020. ‎
[14]
C. Zhao, X. Sun, S. Yang, X. Ren, P. Zhao, and J. McCann, Exploration across small silos: Federated few-shot ‎learning on network edge, IEEE Netw., vol. 36, no. 1, pp. 159–165, 2022. ‎
[15]
F. Chen, M. Luo, Z. Dong, Z. Li, and X. He, Federated meta-learning with fast convergence and efficient communication, arXiv ‎preprint arXiv: 1802.07876, 2019. ‎
[16]
‎A. Fallah, A. Mokhtari, and A. Ozdaglar, Personalized federated learning: A meta-learning approach, ‎arXiv preprint arXiv: 2002.07948, 2020. ‎
[17]
Q. Yang, Y. Liu, T. Chen, and Y. Tong, Federated machine learning: Concept and applications, ACM Trans. ‎Intell. Syst. Technol., vol. 10, no. 2, p. 12, 2019. ‎
[18]
S. Wang, X. Fu, K. Ding, C. Chen, H. Chen, and J. Li, Federated few-shot learning, arXiv preprint ‎‎arXiv: 2306.10234, 2023. ‎
[19]
S. Ji, Y. Tan, T. Saravirta, Z. Yang, Y. Liu, L. Vasankari, S. Pan, G. Long, and A. Walid, Emerging trends in federated learning: From model fusion to federated x learning, arXiv ‎preprint arXiv: 2102.12920, 2024. ‎
[20]
S. Reddi, Z. Charles, M. Zaheer, Z. Garrett, K. Rush, J. Konečný, S. Kumar, and H. B. McMahan, Adaptive federated optimization, arXiv preprint arXiv: 2003.00295, 2021. ‎
[21]
‎T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, Federated optimization in heterogeneous networks, arXiv preprint arXiv: 1812.06127, 2020. ‎
[22]
‎J. Chen, W. Xu, S. Guo, J. Wang, J. Zhang, and H. Wang, FedTune: A deep dive into efficient federated fine-tuning with pre-trained ‎transformers, arXiv preprint arXiv: 2211.08025, 2022. ‎
[23]
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, Attention is all you need, in Proc. 31 st Int. Conf. Neural Information Processing Systems, ‎‎Long Beach, CA, USA, 2017, pp. 6000–6010. ‎
[24]
L. Qu, Y. Zhou, P. P. Liang, Y. Xia, F. Wang, E. Adeli, L. Fei-Fei, and D. Rubin, Rethinking architecture design for tackling data heterogeneity in federated learning, in ‎Proc. 2022 IEEE/CVF Conf. Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp. 10051–10061. ‎
[25]
G. Koch, R. Zemel, and R. Salakhutdinov, Siamese neural networks for one-shot image recognition, https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf, 2023.
[26]
‎J. Snell, K. Swersky, and R. Zemel, Prototypical networks for few-shot learning, in Proc. 31 st Int. Conf. NeuralInformation Processing Systems, Long Beach, CA, USA, 2017, pp. 4080–4090. ‎
[27]
‎ S. X. Hu, D. Li, J. Stühmer, M. Kim, and T. M. Hospedales, Pushing the limits of simple pipelines for few-shot learning: External data and fine-‎tuning make a difference, in Proc. 2022 IEEE/CVF Conf. Computer Vision andPattern Recognition, New Orleans, LA, USA, 2022, pp. 9058–9067. ‎
[28]
A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Transformers for image recognition at scale, ‎arXiv ‎‎preprint arXiv: 2010.11929, 2021. ‎
[29]
C. Finn, P. Abbeel, and S. Levine, Model-agnostic meta-learning for fast adaptation of deep networks, ‎in Proc. 34 th Int. Conf. Machine Learning, Sydney, Australia, 2017, pp. 1126–1135. ‎
[30]
Z. Li, F. Zhou, F. Chen, and H. Li, Meta-SGD: Learning to learn quickly for few-shot learning, arXiv preprint ‎arXiv: 1707.09835, 2017. ‎
[31]
A. Shysheya, J. Bronskill, M. Patacchiola, S. Nowozin, and R. E. Turner, FiT: Parameter efficient few-shot transfer learning for personalized and ‎federated image classification, arXiv preprint arXiv: 2206.08671, 2023. ‎
[32]
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al., ImageNet large scale visual recognition challenge, Int. J. ‎‎Comput. Vis., vol. 115, no. 3, pp. 211–252, 2015. ‎
[33]
E. Perez, F. Strub, H. de Vries, V. Dumoulin, and A. Courville, FiLM: Visual reasoning with a general conditioning layer, in Proc. 32 nd AAAIConf. Artificial Intelligence, New Orleans, LA, USA, 2018, pp. 3942–3951. ‎
[34]
X. Sun, S. Yang, and C. Zhao, Lightweight industrial image classifier based on federated ‎few-shot ‎learning, ‎IEEE Trans. Industr. Inform., vol. 19, no. 6, pp. 7367–7376, 2023‎. ‎
[35]
F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. S. Torr, and T. M. Hospedales, Learning to compare: Relation ‎network for few-shot learning, in Proc. 2018 IEEE/CVFConf. Computer Visionand Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 1199–1208. ‎
[36]
X. He, C. Tan, B. Liu, L. Si, W. Yao, L. Zhao, D. Liu, Q. Zhangli, Q. Chang, K. Li, et al., ‎Dealing with ‎‎heterogeneous 3D MR knee images: A federated few-shot learning ‎method with dual knowledge ‎‎distillation, arXiv preprint arXiv: 2303.14357, 2023‎. ‎
[37]
W. Huang, M. Ye, B. Du, and X. Gao, Few-shot model agnostic federated learning, ‎in Proc. 30 th ‎‎ACM Int. Conf. Multimedia, Lisboa, Portugal, 2022, pp. 7309–7316‎. ‎
[38]
H. Shi, V. Radu, and P. Yang, Lightweight workloads in heterogeneous federated learning ‎via few-shot ‎‎learning, in Proc. 4 th Int. Workshop onDistributed Machine Learning, Paris, France, 2023, pp. 21–26‎. ‎
[39]
‎ K. Ding, J. Wang, J. Li, K. Shu, C. Liu, and H. Liu, Graph prototypical networks for few-shot learning on ‎attributed ‎networks, in Proc. 29 th ACM Int. Conf. Information &KnowledgeManagement, Virtual Event, 2020, pp. 295–304. ‎
[40]
‎K. Ding, Q. Zhou, H. Tong, and H. Liu, Few-shot network anomaly detection via cross-network meta-‎learning, ‎in Proc. Web Conf. 2021, Ljubljana, Slovenia, 2021, pp. 2448–2456. ‎
[41]
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proc. 2016 IEEEConf. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 770–778. ‎
[42]
A. Krizhevsky, Learning multiple layers of features from tiny images, https://api.semanticscholar.org/CorpusID:18268744, 2023.
[43]
B. M. Lake, R. Salakhutdinov, and J. B. Tenenbaum, Human-level concept learning through ‎probabilistic program induction, Science, vol. 350, no. 6266, pp. 1332–1338, 2015. ‎
[44]
Z. Zhu, J. Hong, and J. Zhou, Data-free knowledge distillation for heterogeneous federated learning, in Proc. 38 th Int. Conf. Machine Learning, Virtual Event, 2021, pp. 12878–12889.
Tsinghua Science and Technology
Pages 1539-1551
Cite this article:
Tavassolian F, Abbasi M, Ramezani A, et al. ResFed: An Accurate and Light Federated Multi-Shot Pre-Trained Model on Edge Devices. Tsinghua Science and Technology, 2025, 30(4): 1539-1551. https://doi.org/10.26599/TST.2024.9010042
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return