Neural Dynamics Self-Attention for Spiking Transformers

• URL: http://arxiv.org/abs/2603.19290v1
• Date: Mon, 09 Mar 2026 12:23:37 GMT
• Title: Neural Dynamics Self-Attention for Spiking Transformers
• Abstract summary: Spiking Neural Networks (SNNs) with Transformer architectures offer a promising pathway to balance energy efficiency and performance.<n>Existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference.<n>We propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements.
• Score: 59.57278823240336
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Integrating Spiking Neural Networks (SNNs) with Transformer architectures offers a promising pathway to balance energy efficiency and performance, particularly for edge vision applications. However, existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference. Through theoretical analysis, we attribute both limitations to the Spiking Self-Attention (SSA) mechanism: the lack of locality bias and the need to store large attention matrices. Inspired by the localized receptive fields (LRF) and membrane-potential dynamics of biological visual neurons, we propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements. Specifically, we introduce a LRF method into SSA to assign higher weights to neighboring regions, strengthening local modeling and improving performance. Building on this, we approximate the resulting attention computation via charge-fire-reset dynamics, eliminating explicit attention-matrix storage and reducing inference-time memory. Extensive experiments on visual tasks confirm that our method reduces memory overhead while delivering significant performance improvements. These results establish it as a key unit for achieving energy-efficient Spiking Transformers.

Related papers

• Elastic Spiking Transformers for Efficient Gesture Understanding [6.52225846892392]
  Spiking Neural Networks (SNNs) offer energy-efficient processing of event-based sensor data for healthcare applications.<n>We introduce the Elastic Spiking Transformer, a runtime-adaptive architecture that brings elasticity into the spiking paradigm.<n>We evaluate the approach on CIFAR10/100, CIFAR10-DVS, and the EHWGesture clinical gesture understanding dataset.
  arXiv  Detail & Related papers  (2026-05-04T12:35:52Z)
• Ge$^\ ext{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer [84.8831358775386]
  Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs)<n>Existing paradigms including ANN-SNN Conversion and Spatial-Temporal Backpropagation (STBP) suffer from inherent limitations.<n>We propose Ge$text2$mS-T, a novel architecture implementing grouped computation across temporal, spatial and network structure dimensions.
  arXiv  Detail & Related papers  (2026-04-10T02:58:46Z)
• General Self-Prediction Enhancement for Spiking Neurons [71.01912385372577]
  Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability and trade-offs among performance, efficiency, and biological plausibility.<n>We propose a self-prediction enhanced spiking neuron method that generates an internal prediction current from its input-output history to modulate membrane potential.<n>This design offers dual advantages, it creates a continuous gradient path that alleviates vanishing gradients and boosts training stability and accuracy, while also aligning with biological principles, which resembles distal dendritic modulation and error-driven synaptic plasticity.
  arXiv  Detail & Related papers  (2026-01-29T15:08:48Z)
• Fractional Spike Differential Equations Neural Network with Efficient Adjoint Parameters Training [63.3991315762955]
  Spiking Neural Networks (SNNs) draw inspiration from biological neurons to create realistic models for brain-like computation.<n>Most existing SNNs assume a single time constant for neuronal membrane voltage dynamics, modeled by first-order ordinary differential equations (ODEs) with Markovian characteristics.<n>We propose the Fractional SPIKE Differential Equation neural network (fspikeDE), which captures long-term dependencies in membrane voltage and spike trains through fractional-order dynamics.
  arXiv  Detail & Related papers  (2025-07-22T18:20:56Z)
• Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks [86.28783985254431]
  Spiking neural networks (SNNs) are emerging as a promising alternative to traditional artificial neural networks (ANNs)<n>We propose SpikeSR, which achieves state-of-the-art performance across various remote sensing benchmarks such as AID, DOTA, and DIOR.
  arXiv  Detail & Related papers  (2025-03-06T09:06:06Z)
• Advancing Spatio-Temporal Processing in Spiking Neural Networks through Adaptation [6.233189707488025]
  neural networks on neuromorphic hardware promise orders of less power consumption than their non-spiking counterparts.<n>Standard neuron model for spike-based computation on such systems has long been the integrate-and-fire (LIF) neuron.<n>The root of these so-called adaptive LIF neurons is not well understood.
  arXiv  Detail & Related papers  (2024-08-14T12:49:58Z)
• SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks [22.665939536001797]
  We propose a novel spiking self-attention mechanism named Dual Spike Self-Attention (DSSA) with a reasonable scaling method. Based on DSSA, we propose a novel spiking Vision Transformer architecture called SpikingResformer. We show that SpikingResformer achieves higher accuracy with fewer parameters and lower energy consumption than other spiking Vision Transformer counterparts.
  arXiv  Detail & Related papers  (2024-03-21T11:16:42Z)
• EMN: Brain-inspired Elastic Memory Network for Quick Domain Adaptive Feature Mapping [57.197694698750404]
  We propose a novel gradient-free Elastic Memory Network to support quick fine-tuning of the mapping between features and prediction.<n>EMN adopts randomly connected neurons to memorize the association of features and labels, where the signals in the network are propagated as impulses.<n>EMN can achieve up to 10% enhancement of performance while only needing less than 1% timing cost of traditional domain adaptation methods.
  arXiv  Detail & Related papers  (2024-02-04T09:58:17Z)
• Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patterns [4.8416725611508244]
  Spiking Neural Networks (SNNs) use discrete spike sequences to transmit information, which significantly mimics the information transmission of the brain. This paper introduces the dynamic Burst pattern and designs the Leaky Integrate and Fire or Burst (LIFB) neuron that can make a trade-off between short-time performance and dynamic temporal performance.
  arXiv  Detail & Related papers  (2023-01-29T04:22:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.