EUVIMEDEUVIMED entdecken
Crossref

Dyn-SSM: Towards the Efficient Long Sequence Learning via Bio-interpretable Dynamics in Spiking State Space Models

Yan Zhong, Ruoyu Zhao, Chao Wang, Jiaqi He, Qinghai Guo, Jianguo Zhang, Zhichao Lu, Luziwei Leng

IEEE Transactions on Cognitive and Developmental Systems · 2026 · 1-15

DOI: 10.1109/tcds.2026.3698720 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive and Developmental Systems, 2026. Verfasst von Yan Zhong und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spiking neural networks (SNNs) provide an energy-efficient solution by utilizing the spike-based and sparse nature of biological systems. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on long sequential tasks, until the recent emergence of state space models (SSMs), which offer superior computational efficiency and modeling capability. However, applying the highly capable SSMs to SNNs for long sequences learning poses three major challenges: (1) The membrane potential is determined by the past spiking history of the neuron, leading to reduced efficiency for sequence modeling in parallel computing scenarios. (2) Complex dynamics of biological spiking neurons are crucial for functionality but challenging to simulate and exploit effectively in large networks. (3) It is arduous to maintain high sparsity while achieving high accuracy for spiking neurons without resorting to dense computing, as utilized in artificial neuron-based SSMs. To address them, we propose a sparse, precise and efficient spiking SSM framework, termed SPikE-SSM. For (1), we propose a boundary compression strategy (PMBC) to accelerate the inference of the spiking neuron model, enabling parallel processing for long sequence learning. For (2), we propose a novel and concise neuron model incorporating reset-refractory mechanism to leverage the inherent temporal dimension for dynamic computing with biological interpretability. For (3), we hierarchically integrate the proposed neuron model to the original SSM block, and enhance the dynamics of SPikE-SSM by incorporating trainable thresholds and refractory magnitudes to balance accuracy and sparsity. Extensive experiments verify the effectiveness and robustness of SPikE-SSM on the long range arena benchmarks and large language dataset WikiText-103, showing the potential of dynamic spiking neurons in efficient long sequence learning.

Zitieren

APA

Zhong, Y., Zhao, R., Wang, C., He, J., Guo, Q., Zhang, J., Lu, Z., & Leng, L. (2026). Dyn-SSM: Towards the Efficient Long Sequence Learning via Bio-interpretable Dynamics in Spiking State Space Models. IEEE Transactions on Cognitive and Developmental Systems, 1-15. https://doi.org/10.1109/tcds.2026.3698720

Vancouver

Zhong Y, Zhao R, Wang C, He J, Guo Q, Zhang J, et al. Dyn-SSM: Towards the Efficient Long Sequence Learning via Bio-interpretable Dynamics in Spiking State Space Models. IEEE Transactions on Cognitive and Developmental Systems. 2026:1-15. doi:10.1109/tcds.2026.3698720

BibTeX
@article{Zhong2026,
  author = {Zhong, Yan and Zhao, Ruoyu and Wang, Chao and He, Jiaqi and Guo, Qinghai and Zhang, Jianguo and Lu, Zhichao and Leng, Luziwei},
  title = {Dyn-SSM: Towards the Efficient Long Sequence Learning via Bio-interpretable Dynamics in Spiking State Space Models},
  journal = {IEEE Transactions on Cognitive and Developmental Systems},
  year = {2026},
  pages = {1--15},
  doi = {10.1109/tcds.2026.3698720}
}
Kostenlos starten →