Federated Meta-Learning for Open Set Identification with Privacy Preservation
DOI:
https://doi.org/10.15837/ijccc.2026.3.7033Keywords:
Open-set recognition, Federated meta-learning, Aggregation, Privacy preservationAbstract
Traditional machine learning models typically address closed-set recognition problems. However, in real-world scenarios, open-set recognition challenges frequently arise, where the accuracy of existing methods tends to be low. To address this issue, this paper proposes a versatile classification framework that integrates federated learning and meta-learning to tackle open-set recognition in federated environments. In the proposed methodology, federated meta-learning is first employed to train a global model with strong generalization capabilities across different clients, while preserving data privacy. Then, each local client extracts features and applies a relational network-based classifier to perform classification, obtaining the final prediction results. The local models are updated accordingly, and a coefficient-based aggregation algorithm is designed to update the global model, considering both the aggregation coefficients and classification accuracy. Finally, the server distributes the updated global model back to the clients, who update their local models and proceed to the next training round. To validate the effectiveness of the proposed approach, open-set recognition experiments are conducted on the MNIST, CIFAR-100, and Omniglot datasets. Experimental results demonstrate that the proposed method not only ensures local data privacy but also achieves higher accuracy compared to baseline algorithms such as FedAvg.
References
Modestas, M.; Dzemyda, G. (2024). EfficientNet Convolutional Neural Network with Gram Matrices Modules for Predicting Sadness Emotion, International Journal of Computers, Communications & Control, 19(5), 2024. https://doi.org/10.15837/ijccc.2024.5.6697
Venkatesh, R., Anantharajan, S., Gunasekaran, S. (2023). Multi-gradient boosted adaptive SVMbased prediction of heart disease, International Journal of Computers, Communications & Control, 18(5), 2023. https://doi.org/10.15837/ijccc.2023.5.4994
Liu, Y., Kang, Y., Zou, T. Y., Pu, Y. H., He, Y. Q., Ye, X. Z. (2024). Vertical federated learning: Concepts, advances, and challenges, IEEE Transactions on Knowledge and Data Engineering, 36(7), 3615-5634, 2024. https://doi.org/10.1109/TKDE.2024.3352628
Li, T., Sahu, A. K., Talwalkar, A., Talwalkar, A., Smith, V. (2020). Federated learning: Challenges, methods, and future directions, IEEE signal processing magazine, 37(3), 50-60, 2020. https://doi.org/10.1109/MSP.2020.2975749
Liu, Y., Kang, Y., Xing, C., Yang, Q. (2020). A secure federated transfer learning framework, IEEE Intelligent Systems, 335(4), 70-82, 2020. https://doi.org/10.1109/MIS.2020.2988525
Yang, Q., Liu Y., Chen, T., Tong, Y. (2019). Federated machine learning: Concept and applications, ACM Transactions on Intelligent Systems and Technology (TIST), 10(2), 1-19, 2019. https://doi.org/10.1145/3298981
Li, Y., Chang, T. H., Chi, C. Y. (2020). Secure Federated Averaging Algorithm with Differential Privacy, International Workshop on Machine Learning for Signal Processing (MLSP), 2020. https://doi.org/10.1109/MLSP49062.2020.9231531
Lu, Z., Pan, H., Dai, Y., Si, X., Zhang, Y. (2024). SFederated Learning with Non-IID Data: A Survey, IEEE Internet of Things Journal, 11(1), 19188-19209, 2024. https://doi.org/10.1109/JIOT.2024.3376548
Sattler, F., Müller, K. R., Samek, W. (2020). Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints, IEEE Transactions on Neural Networks and Learning Systems, 31(8), 2740-2753, 2020.
Li, X., Liu, Y., Sun, Y. (2020). Federated Learning with Non-IID Data: A Survey, IEEE Transactions on Neural Networks and Learning Systems, 32(5), 2152-2168, 2020.
Yang, H., Liu, Z., Yang, Q. (2020). A Survey of Federated Learning Systems: Vision, Hype, and Reality for Data Privacy and Security, IEEE Transactions on Knowledge and Data Engineering, 32(9), 1714-1733, 2020.
Kairouz, P., McMahan, H. B., Alistarh, D. (2021). Advances and Open Problems in Federated Learning, Foundations and Trends in Machine Learning, 14(1), 1-210, 2021.
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V. (2018). Federated learning with non-iid data, arXiv preprint arXiv:1806.00582, 2018.
Vilalta, R., Youssef, D. (2002). A perspective view and survey of meta-learning, Artificial intelligence review, 77-95, 2002. https://doi.org/10.1023/A:1019956318069
Hospedales, T., Antoniou, A., Micaelli, P., Storkey, A. (2021). Meta-learning in neural networks: A survey, IEEE transactions on pattern analysis and machine intelligence, 44(9), 5149-5169, 2021.
Vanschoren, J. (2019). Meta-learning, Automated machine learning: methods, systems, challenges, 35-61, 2019. https://doi.org/10.1007/978-3-030-05318-5_2
Vinyals ,O., Blundell ,C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D. (2016). Matching networks for one shot learning, Advances in Neural Information Processing Systems, 3630-3638, 2016.
Snell, J., Swersky, K., Zemel, R. (2017). Prototypical networks for few-shot learning, Advances in Neural Information Processing Systems, 4077-4087, 2017.
Li, X., Chen, M., Yang, Z. (2021). FedMeta: Federated Meta-Learning for Personalization and Federated Learning, IEEE Transactions on Neural Networks and Learning Systems, 32(5), 1740- 1753, 2021.
Yang, Z., Li, Z., Zhang, Y. (2022). Federated Meta-Learning with Recurrent Neural Networks for Time-Series Forecasting, IEEE Transactions on Neural Networks and Learning Systems, 33(6), 2851-2862, 2022.
Acar, D. A. E, Zhao, Y., Zhu, R., Mattina, M., Whatmough, P., Saligrama, V. (2021). Debiasing Model Updates for Improving Personalized Federated Training, International Conference on Machine Learning. PMLR, 21-31, 2021.
Singhal, K., Sidahmed, H., Garrett, Z., Wu, S. S., Rush, K., Prakash, S. (2021). Federated reconstruction: Partially local federated learning, Advances in Neural Information Processing Systems, 34, 2021.
Yue, S., Ren, J., Xin, J., Zhang, D. Y., Zhang, Y. X., Zhuang, W. H. (2022). Efficient Federated Meta-Learning over Multi-Access Wireless Networks, IEEE Journal on Selected Areas in Communications, 2022. https://doi.org/10.1109/JSAC.2022.3143259
Fallah, A., Mokhtari, A., Ribeiro, A. (2020). Personalized federated learning: A meta-learning approach, Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.
Li, T., Sahu, A K., Sanjabi, M., McMahan, H. B. (2020). Federated optimization in heterogeneous networks, Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
Li, X., Xie, L., Liu, Z. (2019). Meta-learning with warping: A fast and efficient model agnostic meta-learning framework, IEEE Transactions on Neural Networks and Learning Systems, 30(9), 2832-2843, 2019.
Chen, X., Song, L. (2020). Meta-learning for multi-task learning: A case study, IEEE Transactions on Neural Networks and Learning Systems, 31(7), 2545-2557, 2020.
Liu, J., Sun, B., Yu, L. (2019). Meta-Learning for Optimizing Neural Networks, IEEE Transactions on Neural Networks and Learning Systems, 30(9), 2832-2843, 2019. https://doi.org/10.1109/TNNLS.2019.2935575
Zhou, Y., Zha, H. (2020). Meta-Learning Optimizers with a Variational Approach, IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(9), 2060-2069, 2020.
Xu, H., Sun, Y., Wen, X. (2021). Meta-Optimizer: Meta-Learning for Optimizing Learning Algorithms, Neural Networks, 136, 128-137, 2021.
Zhou, A., Xu, Z., Li, L. (2019). Memory-Augmented Neural Networks for Few-Shot Learning, IEEE Transactions on Neural Networks and Learning Systems, 30(11), 3427-3439, 2019. https://doi.org/10.1109/TNNLS.2019.2949330
Hu, W., Liu, M. (2021). Learning to Remember for Few-Shot Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(4), 1125-1138, 2021.
Zhang, L., Xie, L., Yang, Y. (2020). Meta-Learning with Memory-Augmented Networks for Robust Few-Shot Classification, Neural Networks, 131, 173-182, 2020.
Deng, L., Zheng, W., Yang, Y. (2020). Federated Meta-Learning for Robust Personalized Federated Learning, Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.
Zhao, Y., Zhang, X., Wang, X. (2020). Federated Meta-Learning with Personalization Layers, Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI), 2020.
Yang, L., Zhang, Y., Zhang, H. (2021). Federated Meta-Learning for Open-Set Recognition, IEEE Transactions on Artificial Intelligence, 2(4), 374-382, 2021.
Wu, W., Shen, J., Zhangm, D. (2022). Federated Meta-Learning with Uncertainty Quantification for Open-Set Classification, Journal of Machine Learning Research, 23(45), 1-25, 2022.
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P., Hospedales, T. (2018). Learning to compare: Relation network for few-shot learning, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1199-1208, 2018. https://doi.org/10.1109/CVPR.2018.00131
Mcmahan, H. B., Moore, E., Ramage, D., Hampson, S., Arcas, B. A. (2017). Communication- Efficient learning of deep networks from decentralized data, Artificial intelligence and statistics, 1273-1282, 2017.
He, K., Zhang, X., Ren, S., et al. (2016). Deep Residual Learning for Image Recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, 2016. https://doi.org/10.1109/CVPR.2016.90
Arivazhagan, M. G., Aggarwal, V., Singh, A. K., et al. (2019). Federated Learning with Personalization Layers, arXiv preprint arXiv:1912.00818, 2019.
Li, X., Jiang,m M., Zhang, X., et al. (2021). Federated Learning on Non-IID Features via Local Batch Normalization, arXiv preprint arXiv:2102.07623, 2021.
Finn, C,. Abbeel, P., Levine S. (2017). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks, International conference on machine learning. PMLR, 2017.
Nichol, A,. Achiam, J., Schulman, J. (2017). On First-Order Meta-Learning Algorithms, arXiv preprint arXiv:1803.02999, 2018.
Additional Files
Published
Issue
Section
License
Copyright (c) 2025 Lang Wu
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
ONLINE OPEN ACCES: Acces to full text of each article and each issue are allowed for free in respect of Attribution-NonCommercial 4.0 International (CC BY-NC 4.0.
You are free to:
-Share: copy and redistribute the material in any medium or format;
-Adapt: remix, transform, and build upon the material.
The licensor cannot revoke these freedoms as long as you follow the license terms.
DISCLAIMER: The author(s) of each article appearing in International Journal of Computers Communications & Control is/are solely responsible for the content thereof; the publication of an article shall not constitute or be deemed to constitute any representation by the Editors or Agora University Press that the data presented therein are original, correct or sufficient to support the conclusions reached or that the experiment design or methodology is adequate.
