EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PriSparK: Privacy-Preserving and Communication-Efficient Federated Spiking Neural Learning via Event-Sparse Adaptive Aggregation

Xin Liu, Honglei Yao, Shanjie Xu, Yuhui Jin, Zijie Pan, Jiamin Zheng, Li Tan

Electronics · 27.07.2026 · 15 (15) · 3311

DOI: 10.3390/electronics15153311 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 27.07.2026. Verfasst von Xin Liu und 6 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning enables collaborative model training without centralizing private data, yet its deployment on edge devices remains constrained by communication overhead, heterogeneous data distributions, and privacy leakage from shared model updates. Spiking neural networks offer an energy-efficient alternative to conventional artificial neural networks by transmitting sparse binary events rather than dense activations, but existing federated spiking learning methods still suffer from inefficient gradient exchange and insufficient privacy protection under non-independent and identically distributed data. This paper proposes PriSparK, a privacy-preserving and communication-efficient federated spiking neural learning framework that jointly exploits temporal event sparsity, adaptive client-side spike-gradient compression, and privacy-calibrated aggregation. The core of PriSparK is a novel Event-Sparse Differentially Private Federated Spiking Optimization algorithm, which converts local surrogate gradients into spike-saliency-aware sparse updates, dynamically allocates communication budgets across layers and time steps, and injects calibrated Gaussian noise after clipping in a low-dimensional event subspace. To mitigate accuracy degradation caused by aggressive compression and privacy perturbation, PriSparK further introduces a membrane-aware error-feedback mechanism and a heterogeneity-adaptive server aggregation rule that weights client updates according to spike activity stability and local distribution drift. Experiments on neuromorphic and vision benchmarks, including N-MNIST, DVS128 Gesture, CIFAR-10, and Fashion-MNIST, show that PriSparK achieves competitive or superior accuracy compared with federated artificial neural and spiking baselines while substantially reducing uplink communication. Under strong privacy constraints, PriSparK maintains stable convergence and improves the accuracy–communication–privacy trade-off, demonstrating its potential for privacy-sensitive edge intelligence with event-driven neural computation.

Zitieren

APA

Liu, X., Yao, H., Xu, S., Jin, Y., Pan, Z., Zheng, J., & Tan, L. (2026). PriSparK: Privacy-Preserving and Communication-Efficient Federated Spiking Neural Learning via Event-Sparse Adaptive Aggregation. Electronics, 15(15), 3311. https://doi.org/10.3390/electronics15153311

Vancouver

Liu X, Yao H, Xu S, Jin Y, Pan Z, Zheng J, et al. PriSparK: Privacy-Preserving and Communication-Efficient Federated Spiking Neural Learning via Event-Sparse Adaptive Aggregation. Electronics. 2026;15(15):3311. doi:10.3390/electronics15153311

BibTeX
@article{Liu2026,
  author = {Liu, Xin and Yao, Honglei and Xu, Shanjie and Jin, Yuhui and Pan, Zijie and Zheng, Jiamin and Tan, Li},
  title = {PriSparK: Privacy-Preserving and Communication-Efficient Federated Spiking Neural Learning via Event-Sparse Adaptive Aggregation},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {15},
  pages = {3311},
  doi = {10.3390/electronics15153311}
}
Kostenlos starten →