2611005643
  • Open Access
  • Article

Fed-VQCS: Vector-Quantized Content-Style State-Space Disentanglement for Federated EEG Generalization

  • Jun Li 1,   
  • Jiping Cui 1,   
  • Rui Yang 1,2,*,   
  • Hanjing Cheng 3 and 
  • Jinling Liang 4

Received: 30 July 2026 | Revised: 31 August 2026 | Accepted: 02 November 2026 | Published: 09 November 2026

Abstract

Federated learning provides a natural framework for decentralized EEG analysis, but learning shared and transferable representations remains challenging because task-relevant neural patterns are often entangled with subject-dependent characteristics in local EEG data. Existing federated EEG methods mainly focus on backbone design, aggregation strategies, or personalized optimization, while representation-level control of what information is globally shared remains insufficiently explored. In this work, we propose Fed-VQCS, a vector-quantized content-style state-space disentanglement framework for robust federated EEG learning. Fed-VQCS introduces a plug-and-play Vector-Quantized Content-Style State-Space (VQCS) module that can be inserted after different EEG feature extractors. Given a latent EEG representation, a bidirectional state-space semantic extractor first produces a continuous task-semantic representation, which is further mapped to globally shared discrete content prototypes through vector quantization. A complementary residual pathway captures variation outside the continuous semantic estimate and is adversarially constrained to suppress task-discriminative information. During federated training, the shared model parameters and content codebook are aggregated globally, while the residual pathway is evaluated within each client’s local training pass. Experiments on BCI Competition IV-2a and PhysioNet, repeated over five random seeds, show consistent improvements in accuracy and Cohen’s κ across four EEG backbones. Comparisons with representative federated learning methods, sensitivity analyses, ablation studies, low-data adaptation, and representation probing further support the effectiveness and robustness of the proposed framework under heterogeneous subject distributions.

References 

  • 1.

    Abiri, R.; Borhani, S.; Sellers, E.W.; et al. A Comprehensive Review of EEG-Based Brain–Computer Interface Paradigms. J. Neural Eng. 2019, 16, 011001. https://doi.org/10.1088/1741-2552/aaf12e.

  • 2.

    Altaheri, H.; Muhammad, G.; Alsulaiman, M.; et al. Deep Learning Techniques for Classification of Electroencephalogram (EEG) Motor Imagery (MI) Signals: A Review. Neural Comput. Appl. 2023, 35, 14681–14722. https://doi.org/10.1007/s00521-021-06352-5.

  • 3.

    Värbu, K.; Muhammad, N.; Muhammad, Y. Past, Present, and Future of EEG-Based BCI Applications. Sensors 2022, 22, 3331. https://doi.org/10.3390/s22093331.

  • 4.

    Yadav, H.; Maini, S. Electroencephalogram Based Brain-Computer Interface: Applications, Challenges, and Opportunities. Multimed. Tools Appl. 2023, 82, 47003–47047. https://doi.org/10.1007/s11042-023-15653-x.

  • 5.

    Hossain, K.M.; Islam, M.A.; Hossain, S.; et al. Status of Deep Learning for EEG-Based Brain–Computer Interface Applications. Front. Comput. Neurosci. 2023, 16, 1006763. https://doi.org/10.3389/fncom.2022.1006763.

  • 6.

    Luo, Y.; Wang, H.; Chen, Z.; et al. Integrating Channel Priors and Shared Pattern Learning for Enhanced Motor Imagery EEG Classification. Neurocomputing 2026, 669, 132532. https://doi.org/10.1016/j.neucom.2025.132532.

  • 7.

    Qin, C.; Yang, R.; Zhu, L.; et al. EEG-Infinity: A Mathematical Modeling-Inspired Architecture for Addressing Cross-Device Challenges in Motor Imagery. IEEE Trans. Neural Syst. Rehabil. Eng. 2025, 33, 4669–4686. https://doi.org/10.1109/tnsre.2025.3635018.

  • 8.

    Liu, B.; Lv, N.; Guo, Y.; et al. Recent Advances on Federated Learning: A Systematic Survey. Neurocomputing 2024, 597, 128019. https://doi.org/10.1016/j.neucom.2024.128019.

  • 9.

    Lyu, L.; Yu, H.; Ma, X.; et al. Privacy and Robustness in Federated Learning: Attacks and Defenses. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 8726–8746. https://doi.org/10.1109/tnnls.2022.3216981.

  • 10.

    Chen, K.; Liu, M.; Zhu, Z.; et al. Distributed Observers for Linear Systems with Communication Noises over Markovian Switching Topologies. Int. J. Syst. Sci. 2025, 56, 1973–1985. https://doi.org/10.1080/00207721.2024.2436639.

  • 11.

    Liu, S.; Wang, L.; Zhang, Y.; et al. Recursive Filtering of Networked Systems with Communication Protocol Scheduling: A Survey. Int. J. Syst. Sci. 2025, 56, 2499–2516. https://doi.org/10.1080/00207721.2024.2448775.

  • 12.

    Chen, W.; Hu, J.; Wu, Z.; et al. A Survey on Fault Detection for Networked Systems under Communication Constraints. Syst. Sci. Control. Eng. 2025, 13, 2460434. https://doi.org/10.1080/21642583.2025.2460434.

  • 13.

    Yang, Q.; Liu, Y.; Chen, T.; et al. Federated Machine Learning. ACM Trans. Intell. Syst. Technol. 2019, 10, 1–19. https://doi.org/10.1145/3298981.

  • 14.

    Zhan, S.; Huang, L.; Luo, G.; et al. A Review on Federated Learning Architectures for Privacy-Preserving AI: Lightweight and Secure Cloud–Edge–End Collaboration. Electronics 2025, 14, 2512. https://doi.org/10.3390/electronics14132512.

  • 15.

    Yan, X.; Wang, C.; Jin, Y. Federated Bimodal Graph Neural Networks for Text-Image Retrieval. Int. J. Netw. Dyn. Intell. 2025, 4, 100009. https://doi.org/10.53941/ijndi.2025.100009.

  • 16.

    Jia, T.; Meng, L.; Li, S.; et al. Federated Motor Imagery Classification for Privacy-Preserving Brain-Computer Interfaces. IEEE Trans. Neural Syst. Rehabil. Eng. 2024, 32, 3442–3451. https://doi.org/10.1109/tnsre.2024.3457504.

  • 17.

    Zhao, P.; Chen, Y.; Ding, D.; et al. Privacy-Preserving Distributed State Estimation for Microgrids Based on Encrypted Measurements under Bit-Rate Constraints. Int. J. Syst. Sci. 2025, 56, 2481–2498. https://doi.org/10.1080/00207721.2024.2448773.

  • 18.

    Gao, P.; Jia, C.; Zhou, A. Encryption–Decryption-Based State Estimation for Nonlinear Complex Networks Subject to Coupled Perturbation. Syst. Sci. Control. Eng. 2024, 12, 2357796. https://doi.org/10.1080/21642583.2024.2357796.

  • 19.

    Zou, L.; Song, B.; Suo, J.; et al. A Survey on Outlier-Resistant State Estimation and Its Applications. Syst. Sci. Control. Eng. 2025, 13, 2474471. https://doi.org/10.1080/21642583.2025.2474471.

  • 20.

    Song, B.; Zhao, S.; Dang, L.; et al. A Survey on Learning from Data with Label Noise via Deep Neural Networks. Syst. Sci. Control. Eng. 2025, 13, 2488120. https://doi.org/10.1080/21642583.2025.2488120.

  • 21.

    Cai, Y.; Yang, X.; Yang, Y.; et al. Leader-Following Privacy-Preserving Consensus Control of Nonlinear Multi-Agent Systems: A State Decomposition Approach. Int. J. Syst. Sci. 2025, 56, 2284–2295. https://doi.org/10.1080/00207721.2024.2445726.

  • 22.

    Wan, Z.; Yang, R.; Huang, M.; et al. A Review on Transfer Learning in EEG Signal Analysis. Neurocomputing 2021, 421, 1–14. https://doi.org/10.1016/j.neucom.2020.09.017.

  • 23.

    Zhan, Y.; Yang, R.; You, J.; et al. A Systematic Literature Review on Incomplete Multimodal Learning: Techniques and Challenges. Syst. Sci. Control. Eng. 2025, 13, 2467083. https://doi.org/10.1080/21642583.2025.2467083.

  • 24.

    Luo, Z.; Wang, Y.; Wang, Z.; et al. Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring. In Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, USA, 17–23 July 2022; Volume 162, pp. 14527–14541.

  • 25.

    Lawhern, V.J.; Solon, A.J.; Waytowich, N.R.; et al. EEGNet: A Compact Convolutional Neural Network for EEG-Based Brain–Computer Interfaces. J. Neural Eng. 2018, 15, 056013. https://doi.org/10.1088/1741-2552/aace8c.

  • 26.

    Riyad, M.; Khalil, M.; Adib, A. MI-EEGNET: A Novel Convolutional Neural Network for Motor Imagery Classification. J. Neurosci. Methods 2021, 353, 109037. https://doi.org/10.1016/j.jneumeth.2020.109037.

  • 27.

    Ding, Y.; Robinson, N.; Zhang, S.; et al. TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition. IEEE Trans. Affect. Comput. 2023, 14, 2238–2250. https://doi.org/10.1109/taffc.2022.3169001.

  • 28.

    Yue, J.; Xiao, X.; Wang, K.; et al. Augmenting Electroencephalogram Transformer for Steady-State Visually Evoked Potential-Based Brain–Computer Interfaces. Cyborg Bionic Syst. 2025, 6, 0379. https://doi.org/10.34133/cbsystems.0379.

  • 29.

    Gao, M.; Gao, C.; Yao, Z.; et al. FA-STTM: A Hybrid Transformer-Mamba Network for Motor Imagery EEG Classification. Neurocomputing 2026, 669, 132481. https://doi.org/10.1016/j.neucom.2025.132481.

  • 30.

    Xu, C.; Liu, H.; Qi, W. EEG Emotion Recognition Based on Federated Learning Framework. Electronics 2022, 11, 3316. https://doi.org/10.3390/electronics11203316.

  • 31.

    Yin, K.; Ding, Z.; Yang, X.; et al. Sleep Staging Method for Imbalanced EEG Data Based on Differential Privacy Federated Learning. Int. J. Artif. Intell. Tools 2022, 31, 2240018. https://doi.org/10.1142/s0218213022400188.

  • 32.

    Ma, B.; Duan, L.; Huang, Z.; et al. A Federated Semi-Supervised Automatic Sleep Staging Method Based on Relationship Knowledge Sharing. Expert Syst. Appl. 2024, 237, 121427. https://doi.org/10.1016/j.eswa.2023.121427.

  • 33.

    Moon, S.; Kim, T.S.; Ryu, J.; et al. Federated Learning for Sleep Stage Classification on Edge Devices via a Model-Agnostic Meta-Learning-Based Pre-Trained Model. In Proceedings of the 2023 IEEE 13th International Conference on Consumer Electronics-Berlin (ICCE-Berlin), Berlin, Germany, 3–5 September 2023; pp. 188–192. https://doi.org/10.1109/icceberlin58801.2023.10375664.

  • 34.

    López Bernal, S.; Hidalgo Rogel, J.M.; Martínez Beltrán, E.T.; et al. Privacy-Preserving Hierarchical Federated Learning with Biosignals to Detect Drowsiness while Driving. Neural Comput. Appl. 2024, 36, 20425–20437. https://doi.org/10.1007/s00521-024-10282-3.

  • 35.

    Liu, R.; Chen, Y.; Li, A.; et al. Aggregating Intrinsic Information to Enhance BCI Performance through Federated Learning. Neural Netw. 2024, 172, 106100. https://doi.org/10.1016/j.neunet.2024.106100.

  • 36.

    Liang, Y.; Chen, Y.; Pan, D.; et al. Privacy-Preserving Distributed Entropy Filtering for Microgrids with Innovation Decomposition. Int. J. Netw. Dyn. Intell. 2025, 4, 100004. https://doi.org/10.53941/ijndi.2025.100004.

  • 37.

    Aziz, A.; Chhaglani, B.; Radmehr, A.; et al. Hardware-Assisted Privacy-Preserving Multi-Channel EEG Computational Headwear. In Proceedings of the 2024 IEEE 20th International Conference on Body Sensor Networks (BSN), Chicago, IL, USA, 15–17 October 2024; pp. 1–4. https://doi.org/10.1109/bsn63547.2024.10780473.

  • 38.

    Zhang, W.; Wang, Z.; Wu, D. Multi-Source Decentralized Transfer for Privacy-Preserving BCIs. IEEE Trans. Neural Syst. Rehabil. Eng. 2022, 30, 2710–2720. https://doi.org/10.1109/tnsre.2022.3207494.

  • 39.

    Zhong, J.; Chen, H.Y.; Chao, W.L. Making Batch Normalization Great in Federated Deep Learning. arXiv 2023, arXiv:2303.06530v4.

  • 40.

    Chen, H.; Xu, T.; Wu, X.; et al. Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning. In Proceedings of the 42nd International Conference on Machine Learning, Vancouver, BC, Canada, 13–19 July 2025; Volume 267, pp. 9500–9515. https://proceedings.mlr.press/v267/chen25by.html.

  • 41.

    Bao, W.; Wei, T.; Wang, H.; et al. Adaptive Test-Time Personalization for Federated Learning. In Proceedings of the Advances in Neural Information Processing Systems 36, New Orleans, LA, USA, 10–16 December 2023; Volume 36, pp. 77882–77914. https://doi.org/10.52202/075280-3403.

  • 42.

    Perslev, M.; Darkner, S.; Kempfner, L.; et al. U-Sleep: Resilient High-Frequency Sleep Staging. npj Digit. Med. 2021, 4, 72. https://doi.org/10.1038/s41746-021-00440-5.

  • 43.

    Qin, C.; Yang, R.; You, W.; et al. EEGUnity: Open-Source Tool in Facilitating Unified EEG Datasets toward Large-Scale EEG Model. IEEE Trans. Neural Syst. Rehabil. Eng. 2025, 33, 1653–1663. https://doi.org/10.1109/tnsre.2025.3565158.

  • 44.

    Hu, Y.; Zhang, C.; Liu, S. Privacy-Preserving Distributed Recursive Filtering for State-Saturated Systems with Quantization Effects. Int. J. Netw. Dyn. Intell. 2025, 4, 100012. https://doi.org/10.53941/ijndi.2025.100012.

  • 45.

    Fan, H.; Liu, S.; Cao, X.; et al. A Prototype-Guided Federated Learning Based Fault Diagnosis Method of Mechanical Transmission System under Label Distribution Skew. Neurocomputing 2025, 656, 131532. https://doi.org/10.1016/j.neucom.2025.131532.

  • 46.

    Goldberger, A.L.; Amaral, L.A.N.; Glass, L.; et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 2000, 101, e215–e220. https://doi.org/10.1161/01.cir.101.23.e215.

  • 47.

    Brunner, C.; Leeb, R.; Müller-Putz, G.; et al. BCI Competition 2008–Graz data set A. Available online: https://www.bbci.de/competition/iv/desc 2a.pdf (accessed on 7 November 2026).

  • 48.

    Schirrmeister, R.T.; Springenberg, J.T.; Fiederer, L.D.J.; et al. Deep Learning with Convolutional Neural Networks for EEG Decoding and Visualization. Hum. Brain Mapp. 2017, 38, 5391–5420. https://doi.org/10.1002/hbm.23730.

  • 49.

    Song, Y.; Zheng, Q.; Liu, B.; et al. EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization. IEEE Trans. Neural Syst. Rehabil. Eng. 2023, 31, 710–719. https://doi.org/10.1109/tnsre.2022.3230250.

  • 50.

    Zhao, W.; Jiang, X.; Zhang, B.; et al. CTNet: A Convolutional Transformer Network for EEG-Based Motor Imagery Classification. Sci. Rep. 2024, 14, 20237. https://doi.org/10.1038/s41598-024-71118-7.

Share this article:
How to Cite
Li, J.; Cui, J.; Yang, R.; Cheng, H.; Liang, J. Fed-VQCS: Vector-Quantized Content-Style State-Space Disentanglement for Federated EEG Generalization. International Journal of Network Dynamics and Intelligence 2026, 5 (4), 26. https://doi.org/10.53941/ijndi.2026.100026.
RIS
BibTex
Copyright & License
article copyright Image
Copyright (c) 2026 by the authors.
Article Metrics
39
Article Views
0
Citations