SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyState Space ModelsSimilar Papers 제목 키워드 기반
SPARTA: Advancing Sparse Attention in Spiking Neural Networks via Spike-Timing-Based Prioritization
Current Spiking Neural Networks (SNNs) underutilize the temporal dynamics inherent in spike-based processing, relying primarily on rate coding while overlooking precise timing information that provides rich computational…
Computational EfficiencyVision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models
Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token interactions remain fundamentally misaligned with the sparse and event-d…
Long-range modelingS3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition
Skeleton-based action recognition is crucial for multimedia applications but heavily relies on power-hungry Artificial Neural Networks (ANNs), limiting their deployment on resource-constrained edge devices. Spiking Neura…
Action RecognitionP-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks
Spiking neural networks (SNNs) are posited as a computationally efficient and biologically plausible alternative to conventional neural architectures, with their core computational framework primarily using the leaky int…
Computational EfficiencyState Space ModelsRobust computation with rhythmic spike patterns
Information coding by precise timing of spikes can be faster and more energy-efficient than traditional rate coding. However, spike-timing codes are often brittle, which has limited their use in theoretical neuroscience …