SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning

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

Keywords: state space models, spiking neural network, long sequence modeling, language modeling

TL;DR: The work propsed a sparse, precise and efficient spiking state space model for long sequence learning, using parallel boundary compression and refractory spiking neurons.

Abstract: Spiking neural networks (SNNs) provide a low-power, 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: ❶ The membrane potential is determined by the past spiking history of the neuron, leading to reduced efficiency for sequence modeling in parallel computing scenarios. ❷ Complex dynamics of biological spiking neurons are crucial for functionality but challenging to simulate and exploit effectively in large networks. ❸ 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 these challenges, we propose a sparse, precise and efficient spiking SSM framework, termed SPikE-SSM. For ❶, we propose a boundary compression strategy (PMBC) to accelerate the inference of the spiking neuron model, enabling parallel processing for long sequence learning. For ❷, 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 ❸, 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 illustrate 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. The code will be publicly available.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9109