Congestion-Aware Dynamic Axonal Delay for Spiking Neural Networks

• URL: http://arxiv.org/abs/2605.01291v2
• Date: Thu, 07 May 2026 12:28:37 GMT
• Title: Congestion-Aware Dynamic Axonal Delay for Spiking Neural Networks
• Abstract summary: Spiking Neural Networks (SNNs) are widely regarded as an energy-efficient paradigm for modeling and processing temporal and event-driven information.<n>We propose a Congestion-Aware Dynamic Axonal Delay (CADAD) mechanism, which decomposes the delay into a channel-wise static base delay for temporal structuring.<n> Experiments on speech benchmarks, including the Spiking Heidelberg dataset, demonstrate that congestion-aware delays into synaptic signal transmission effectively improves accuracy on temporal tasks.
• Score: 11.139375968984156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spiking Neural Networks (SNNs) are widely regarded as an energy-efficient paradigm for modeling and processing temporal and event-driven information. Incorporating delays in SNNs has been proven to be an effective mechanism for improving spike alignment in event-driven tasks. However, existing delay learning approaches predominantly assign static delays to individual synapses, resulting in a large number of delay parameters and limited adaptability to input-dependent activity dynamics. To this end, we propose a Congestion-Aware Dynamic Axonal Delay (CADAD) mechanism, which decomposes the delay into a channel-wise static base delay for temporal structuring and a global, activity-conditioned shift that dynamically regulates the state update rate under varying spike intensities. The delay parameters are learned using differentiable linear interpolation and discretized at inference time, preserving the benefits of dynamic delay modulation while incurring only minimal additional cost. Experiments on speech benchmarks, including the Spiking Heidelberg Dataset, Spiking Speech Commands, and Google Speech Commands, demonstrate that introducing congestion-aware delays into synaptic signal transmission effectively improves accuracy on temporal tasks, notably achieving 93.75% accuracy on SHD, 80.69% accuracy on SSC, and 95.58% on GSC-35, while reducing the parameter count by approximately 50% compared to state-of-the-art delay-based methods with the same architecture.

Related papers

• Sparse Axonal and Dendritic Delays Enable Competitive SNNs for Keyword Classification [5.928605435529651]
  Training transmission delays in spiking neural networks (SNNs) has been shown to substantially improve their performance on complex temporal tasks.<n>We show that learning either axonal or dendritic delays enables deep feedforward SNNs to reach accuracy comparable to existing synaptic delay learning approaches.
  arXiv  Detail & Related papers  (2026-02-10T12:57:02Z)
• Three factor delay learning rules for spiking neural networks [0.42970700836450487]
  We introduce synaptic and axonal delays to integrate leaky and fire (LIF)-based feedforward and recurrent SNNs.<n>We propose three-constrained learning rules to simultaneously learn delay parameters online.<n>Our findings benefit the design of power and area-constrained neuromorphic processors by enabling on-device learning and lowering memory requirements.
  arXiv  Detail & Related papers  (2026-01-02T12:28:53Z)
• TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration [64.32072516882947]
  Diffusion Policy excels in embodied control but suffers from high inference latency and computational cost.<n>We propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP)<n>TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz.
  arXiv  Detail & Related papers  (2025-12-13T07:53:14Z)
• Delays in Spiking Neural Networks: A State Space Model Approach [2.309307613420651]
  Spiking neural networks (SNNs) are biologically inspired, event-driven models suitable for processing temporal data.<n>We propose a general framework for incorporating delays into SNNs through additional state variables.<n>We show that the proposed mechanism matches the performance of existing delay-based SNNs while remaining computationally efficient.
  arXiv  Detail & Related papers  (2025-12-01T17:26:21Z)
• An Exact Gradient Framework for Training Spiking Neural Networks [0.7366405857677227]
  Spiking neural networks inherently rely on the precise timing of discrete spike events for information processing.<n>We propose an event-driven learning framework that computes exact loss gradients with respect to synaptic weights and transmission delays.<n>Experiments on multiple benchmarks demonstrate significant gains in accuracy (up to 7%), timing precision, and robustness compared to existing methods.
  arXiv  Detail & Related papers  (2025-07-08T11:55:27Z)
• Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons [69.73249913506042]
  This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons to process time-domain signals directly.<n>By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity.<n> Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs.
  arXiv  Detail & Related papers  (2025-06-24T21:14:59Z)
• Efficient Synaptic Delay Implementation in Digital Event-Driven AI Accelerators [1.260842513389711]
  We introduce Shared Circular Delay Queue (SCDQ), a novel hardware structure for supporting synaptic delays on digital neuromorphic accelerators.<n>Our analysis and hardware results show that it scales better in terms of memory, than current commonly used approaches, and is more amortizable to algorithm- hardware co-optimizations.
  arXiv  Detail & Related papers  (2025-01-23T12:30:04Z)
• DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware [1.5226147562426895]
  Spiking neural networks (SNNs) inherently rely on the timing of signals for representing and processing information.<n>We propose DelGrad, an event-based method to compute exact loss gradients for both synaptic weights and delays.<n>We experimentally demonstrate the memory efficiency and accuracy benefits of adding delays to SNNs on noisy mixed-signal hardware.
  arXiv  Detail & Related papers  (2024-04-30T00:02:34Z)
• Data-Driven Room Acoustic Modeling Via Differentiable Feedback Delay Networks With Learnable Delay Lines [46.2770645198924]
  We introduce a novel method for finding the parameters of a Feedback Delay Network (FDN) The proposed approach involves the implementation of a differentiable FDN with trainable delay lines. We show that the proposed method yields time-invariant frequency-independent FDNs capable of closely matching the desired acoustical characteristics.
  arXiv  Detail & Related papers  (2024-03-29T10:48:32Z)
• FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization [78.46088089185156]
  Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. Existing approaches penalize emission delay by manipulating per-token or per-frame probability prediction in sequence transducer models. We propose a sequence-level emission regularization method, named FastEmit, that applies latency regularization directly on per-sequence probability in training transducer models.
  arXiv  Detail & Related papers  (2020-10-21T17:05:01Z)
• Adaptive Gradient Method with Resilience and Momentum [120.83046824742455]
  We propose an Adaptive Gradient Method with Resilience and Momentum (AdaRem) AdaRem adjusts the parameter-wise learning rate according to whether the direction of one parameter changes in the past is aligned with the direction of the current gradient. Our method outperforms previous adaptive learning rate-based algorithms in terms of the training speed and the test error.
  arXiv  Detail & Related papers  (2020-10-21T14:49:00Z)
• Learn to cycle: Time-consistent feature discovery for action recognition [83.43682368129072]
  Generalizing over temporal variations is a prerequisite for effective action recognition in videos. We introduce Squeeze Re Temporal Gates (SRTG), an approach that favors temporal activations with potential variations. We show consistent improvement when using SRTPG blocks, with only a minimal increase in the number of GFLOs.
  arXiv  Detail & Related papers  (2020-06-15T09:36:28Z)

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.