A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 19.2, Top 1 (SCI Q1)
    CiteScore: 28.2, Top 1% (Q1)
    Google Scholar h5-index: 95， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2026  > In Press, Accepted Manuscript
L. Li, W. Lu, and W. Pedrycz, “Deep fuzzy c-means clustering in a federated heterogeneous scenario,” IEEE/CAA J. Autom. Sinica, early access, 2026. doi: 10.1109/JAS.2025.125561
Citation: L. Li, W. Lu, and W. Pedrycz, “Deep fuzzy c-means clustering in a federated heterogeneous scenario,” IEEE/CAA J. Autom. Sinica, early access, 2026. doi: 10.1109/JAS.2025.125561
shu

Deep Fuzzy C-Means Clustering in a Federated Heterogeneous Scenario

doi: 10.1109/JAS.2025.125561
Funds:  This work was supported in part by the National Natural Science Foundation of China (62073056, 61876029 and 62473074) in part by the Applied Basic Research Program Project of Liaoning Province (2023JH2/101300207), and in part by the Key Field Innovation Team Project of Dalian (2021RT14)
More Information
    Abstract
  • In federated deep fuzzy C-means (FCM) clustering, conventional federated averaging (FedAvg) struggles with non-independent and identically distributed (non-IID) data and dynamic device participation, leading to model drift and performance degradation during global aggregation. To address this challenge, we propose FedFCD, a federated deep FCM clustering method featuring a novel aggregation mechanism. FedFCD equips each client with a hybrid architecture comprising a contrastive autoencoder (CtAE) and an FCM network (FCMNet), which collaboratively learn stable low-dimensional embeddings and refine soft clustering assignments iteratively. At the server side, we design a two-phase aggregation strategy integrating Bayesian ensemble learning and knowledge distillation (KD). First, the Bayesian aggregation mechanism probabilistically fuses heterogeneous local models’ inferences into a consensus assignment by treating each client’s model as a candidate hypothesis, thereby constructing a posterior distribution over the global model space through iterative evidence accumulation. Subsequently, dual-source distillation harmonizes pseudo-labels derived from the Bayesian consensus with ground-truth labels from limited shared data, enabling the global model to align its predictions with both semantic anchors and aggregated soft assignments while preserving privacy through distillation loss. Comparative experiments on benchmark datasets demonstrate that FedFCD outperforms baseline methods in clustering accuracy and exhibits enhanced stability under varying conditions, including data heterogeneity, device numbers, and device dropout.

     

    • FullText(HTML)
  • loading
    • References(51)
  • [1]
    M. Qi, Z. Wang, Q.-L. Han, J. Zhang, S. Chen, and Y. Xiang, “Privacy protection for blockchain-based healthcare IOT systems: A survey,” IEEE/CAA J. Autom. Sinica, vol.11, no. 8, pp. 1757−1776, 2024.
    [2]
    A. Chaddad, Q. Lu, J. Li, Y. Katib, R. Kateb, C. Tanougast, A. Bouridane, and A. Abdulkadir, “Explainable, domain-adaptive, and federated artificial intelligence in medicine,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, pp. 859–876, 2023. doi: 10.1109/JAS.2023.123123
    [3]
    R. Zou, Y. Zhang, Y. Zhang, Y. Lu, M. Li, and Y.-M. Cheung, “Federated clustering with unknown number of clusters,” in Proc. 6th Int. Conf. Data-Driven Optimization of Complex Systems. Hangzhou, China: IEEE, 2024, pp. 671–677.
    [4]
    Y. Ren, X. Chen, J. Xu, J. Pu, Y. Huang, X. Pu, C. Zhu, X. Zhu, Z. Hao, and L. He, “A novel federated multi-view clustering method for unaligned and incomplete data fusion,” Information Fusion, vol. 108, p. 102357, 2024. doi: 10.1016/j.inffus.2024.102357
    [5]
    W. Pedrycz, Granular Computing: Analysis and Design of Intelligent Systems. Boca Raton: CRC Press, 2018.
    [6]
    J. L. C. Brcena, F. Marcelloni, A. Renda, A. Bechini, and P. Ducange, “A federated fuzzy C-means clustering algorithm,” in Proc. Int. Workshop on Fuzzy Logic and Applications, 2021.
    [7]
    J. L. Corcuera Bárcena, F. Marcelloni, A. Renda, A. Bechini, and P. Ducange, “Federated C-means and fuzzy C-means clustering algorithms for horizontally and vertically partitioned data,” IEEE Trans. Artificial Intelligence, pp. 1–15, 2024.
    [8]
    W. Pedrycz, “Federated FCM: Clustering under privacy requirements,” IEEE Trans. Fuzzy Systems, vol. 30, no. 8, pp. 3384–3388, 2021.
    [9]
    M. Stallmann and A. Wilbik, “Towards federated clustering: A federated fuzzy C-means algorithm (FFCM),” arXiv preprints arXiv: 2201.07316, 2022.
    [10]
    J. Yan, J. Liu, Y.-Z. Ning, and Z.-Y. Zhang, “SDA-FC: Bridging federated clustering and deep generative model,” Information Sciences, vol. 681, p. 121203, 2024. doi: 10.1016/j.ins.2024.121203
    [11]
    J. Yan, J. Liu, and Z.-Y. Zhang, “CCFC: Bridging federated clustering and contrastive learning,” arXiv preprint arXiv: 2401.06634, 2024.
    [12]
    N. Hasan, M. G. R. Alam, S. H. Ripon, P. H. Pham, and M. M. Hassan, “An autoencoder-based confederated clustering leveraging a robust model fusion strategy for federated unsupervised learning,” Information Fusion, vol. 115, p. 102751, 2025. doi: 10.1016/j.inffus.2024.102751
    [13]
    J. Chung, K. Lee, and K. Ramchandran, “Federated unsupervised clustering with generative models,” in Proc. AAAI Int. Workshop on Trustable, Verifiable and Auditable Federated Learning, 2022.
    [14]
    L. Collins, H. Hassani, A. Mokhtari, and S. Shakkottai, “Exploiting shared representations for personalized federated learning,” in Proc. Int. Conf. Machine Learning. New York: USA PMLR, 2021, pp. 2089–2099.
    [15]
    Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798–1828, 2013. doi: 10.1109/TPAMI.2013.50
    [16]
    M. Sadeghi and N. Armanfard, “IDECF: Improved deep embedding clustering with deep fuzzy supervision,” in Proc. IEEE Int. Conf. Image Processing. Auchorage, USA: IEEE, 2021, pp. 1009–1013.
    [17]
    S. Rifai, P. Vincent, X. Muller, X. Glorot, and Y. Bengio, “Contractive auto-encoders: Explicit invariance during feature extraction,” in Proc. the 28th International Conf. Machine Learning, 2011, pp. 833–840.
    [18]
    T. Lin, L. Kong, S. U. Stich, and M. Jaggi, “Ensemble distillation for robust model fusion in federated learning,” Advances in Neural Information Processing Systems, vol. 33, pp. 2351–2363, 2020.
    [19]
    H.-Y. Chen and W.-L. Chao, “FEDBE: Making Bayesian model ensemble applicable to federated learning,” arXiv preprints arXiv: 2009.01974, 2020.
    [20]
    Y. Zhang, H. Chen, Z. Lin, Z. Chen, and J. Zhao, “LCFED: An efficient clustered federated learning framework for heterogeneous data,” arXiv preprint arXiv: 2501.01850, 2025.
    [21]
    Y. Zhang, H. Chen, Z. Lin, Z. Chen, and J. Zhao, “FedAC: An adaptive clustered federated learning framework for heterogeneous data,” arXiv preprint arXiv: 2403.16460, 2024.
    [22]
    Y. Zhou, M. Shi, Y. Tian, Y. Li, Q. Ye, and J. Lv, “Federated CINN clustering for accurate clustered federated learning,” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing. Seoul, South Korea: IEEE, 2024, pp. 5590–5594.
    [23]
    D. Yao, W. Pan, Y. Dai, Y. Wan, X. Ding, C. Yu, H. Jin, Z. Xu, and L. Sun, “FEDGKD: Toward heterogeneous federated learning via global knowledge distillation,” IEEE Trans. Computers, vol. 73, no. 1, pp. 3–17, 2023.
    [24]
    X. Li, B. Chen, and W. Lu, “FedDKD: Federated learning with decentralized knowledge distillation,” Applied Intelligence, vol. 53, pp. 18547−18563, 2023.
    [25]
    T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated optimization in heterogeneous networks,” Proc. Machine Learning and Systems, vol. 2, pp. 429–450, 2020.
    [26]
    J. Wang, Q. Liu, H. Liang, G. Joshi, and H. V. Poor, “Tackling the objective inconsistency problem in heterogeneous federated optimization,” Advances in Neural Information Processing Systems, vol. 33, pp. 7611–7623, 2020.
    [27]
    Q. Li, B. He, and D. Song, “Model-contrastive federated learning,” in Proc. the IEEE/CVF Conf. Computer Vision and Pattern Recognition, Nashvill. USA: IEEE, 2021, pp. 10708–10717.
    [28]
    H. Yang, J. Li, M. Hao, W. Zhang, H. He, and A. K. Sangaiah, “An efficient personalized federated learning approach in heterogeneous environments: A reinforcement learning perspective,” Scientific Reports, vol. 14, no. 1, p. 28877, 2024. doi: 10.1038/s41598-024-80048-3
    [29]
    F. Yu, L. Wang, B. Zeng, K. Zhao, and R. Yu, “Personalized and privacy-enhanced federated learning framework via knowledge distillation,” Neurocomputing, vol. 575, p. 127290, 2024. doi: 10.1016/j.neucom.2024.127290
    [30]
    M. Chen, X. Wu, X. Tang, T. He, Y.-S. Ong, Q. Liu, Q. Lao, and H. Yu, “Free-rider and conflict aware collaboration formation for cross-silo federated learning,” arXiv preprint arXiv: 2410.19321, 2024.
    [31]
    S. Tan, H. Cheng, X. Wu, H. Yu, T. He, Y. S. Ong, C. Wang, and X. Tao, “Fedcompetitors: Harmonious collaboration in federated learning with competing participants,” in Proc. the AAAI Conf. Artificial Intelligence, vol. 38, no. 14, 2024, pp. 15231–15239.
    [32]
    J. Xie, R. Girshick, and A. Farhadi, “Unsupervised deep embedding for clustering analysis,” in Int. Conf. Machine Learning. PMLR, 2016, pp. 478–487.
    [33]
    B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial Intelligence and Statistics. PMLR, 2017, pp. 1273–1282.
    [34]
    X. Guo, L. Gao, X. Liu, and J. Yin, “Improved deep embedded clustering with local structure preservation,” in IJCAI’17: Proc. the 26th Int. Joint Conf. Artifical Intelligence, 2017, pp. 1753–1759.
    [35]
    L. Van Der Maaten, “Learning a parametric embedding by preserving local structure.” in Proc. J. Mach. Learn. Res. Artif. Intell. Statist, 2009, pp. 384–391.
    [36]
    R. Sundareswaran, J. Herrera-Gerena, J. Just, and A. Jannesari, “Cluster analysis with deep embeddings and contrastive learning,” arXiv preprint arXiv: 2109.12714, 2021.
    [37]
    X. Deng, D. Huang, D.-H. Chen, C.-D. Wang, and J.-H. Lai, “Strongly augmented contrastive clustering,” Pattern Recognition, vol. 139, p. 109470, 2023. doi: 10.1016/j.patcog.2023.109470
    [38]
    X. Guo, X. Liu, E. Zhu, and J. Yin, “Deep clustering with convolutional autoencoders, ” in Proc. Neural Information Processing: 24th Int. Conf., ICONIP, Guangzhou, China, Springer, 2017, pp. 373–382.
    [39]
    W. J. Maddox, P. Izmailov, T. Garipov, D. P. Vetrov, and A. G. Wilson, “A simple baseline for Bayesian uncertainty in deep learning,” Advances in Neural Information Processing Systems, vol. 32, 2019.
    [40]
    J. Hammersley, Monte Carlo Methods. Springer Science & Business Media, 2013.
    [41]
    Y. Yang, D. Xu, F. Nie, S. Yan, and Y. Zhuang, “Image clustering using local discriminant models and global integration,” IEEE Trans. Image Processing, vol. 19, no. 10, pp. 2761–2773, 2010. doi: 10.1109/TIP.2010.2049235
    [42]
    N. Zeng, X. Li, P. Wu, H. Li, and X. Luo, “A novel tensor decomposition-based efficient detector for low-altitude aerial objects with knowledge distillation scheme,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 2, pp. 487–501, 2024. doi: 10.1109/JAS.2023.124029
    [43]
    P. Wu, H. Li, L. Hu, J. Ge, and N. Zeng, “A local-global attention fusion framework with tensor decomposition for medical diagnosis,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 6, pp. 1536–1538, 2024. doi: 10.1109/JAS.2023.124167
    [44]
    D. Berthelot, N. Carlini, I. Goodfellow, N. Papernot, A. Oliver, and C. A. Raffel, “Mixmatch: A holistic approach to semi-supervised learning,” Advances in Neural Information Processing Systems, vol. 32, 2019.
    [45]
    Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” in Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. doi: 10.1109/5.726791
    [46]
    H. Xiao, K. Rasul, and R. Vollgraf, “Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms,” arXiv preprint arXiv: 1708.07747, 2017.
    [47]
    J. Demšar, “Statistical comparisons of classifiers over multiple data sets,” The J. Machine Learning Research, vol. 7, pp. 1–30, 2006.
    [48]
    T. He, Y. Liu, Y.-S. Ong, X. Wu, and X. Luo, “Polarized message-passing in graph neural networks,” Artificial Intelligence, vol. 331, p. 104129, 2024. doi: 10.1016/j.artint.2024.104129
    [49]
    S. Ding, B. Wu, L. Ding, X. Xu, L. Guo, H. Liao, and X. Wu, “Towards faster deep graph clustering via efficient graph auto-encoder,” ACM Trans. Knowledge Discovery From Data, vol. 18, no. 8, pp. 1–23, 2024.
    [50]
    T. He, Y. S. Ong, and L. Bai, “Learning conjoint attentions for graph neural nets, ” vol. 34. Curran Associates, Inc., 2021, pp. 2641–2653.
    [51]
    J. Liu, L. Wei, X. Xie, E. Tian, and S. Fei, “Quantized stabilization for t–s fuzzy systems with hybrid-triggered mechanism and stochastic cyber-attacks,” IEEE Trans. Fuzzy Systems, vol. 26, no. 6, pp. 3820–3834, 2018. doi: 10.1109/TFUZZ.2018.2849702
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(10)  / Tables(6)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (67) PDF downloads(1) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return