Collapse or Preserve: Data-Dependent Temporal Aggregation for Spiking Neural Network Acceleration

• URL: http://arxiv.org/abs/2603.13810v1
• Date: Sat, 14 Mar 2026 07:30:22 GMT
• Title: Collapse or Preserve: Data-Dependent Temporal Aggregation for Spiking Neural Network Acceleration
• Abstract summary: Spike sparsity is widely believed to enable efficient spiking neural network (SNN) inference on GPU hardware.<n>We demonstrate this is an illusion: SIMD architectures cannot exploit the fine-grained, unstructured sparsity of i.i.d. binary spikes.<n>We propose Temporal Aggregated Convolution (TAC), which exploits convolution linearity to pre-aggregate $K$ spike frames before a single convolution call.
• Score: 1.1597621848542221
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spike sparsity is widely believed to enable efficient spiking neural network (SNN) inference on GPU hardware. We demonstrate this is an illusion: five distinct sparse computation strategies on Apple M3 Max all fail to outperform dense convolution, because SIMD architectures cannot exploit the fine-grained, unstructured sparsity of i.i.d. binary spikes. Instead, we propose Temporal Aggregated Convolution (TAC), which exploits convolution linearity to pre-aggregate $K$ spike frames before a single convolution call, reducing $T$ calls to $T/K$. On rate-coded data, TAC achieves 13.8times speedup with +1.6% accuracy on MNIST and +5.4% on Fashion-MNIST -- a simultaneous improvement in both speed and accuracy. However, on event-based data where the temporal dimension carries genuine motion information, TAC's temporal collapse is harmful. We therefore introduce TAC-TP (Temporal Preservation), which shares each group's convolution output across K independent LIF steps, preserving full temporal resolution for downstream layers. On DVS128-Gesture, TAC-TP achieves 95.1% accuracy (vs. 96.3% baseline) with 50% fewer convolution calls, while standard TAC drops to 91.3%. Our key finding is that the optimal temporal aggregation strategy is data-dependent: collapse the temporal dimension for rate-coded data (noise reduction) but preserve it for event data (information retention). Speedup is hardware-agnostic: TAC achieves 11.0times on NVIDIA V100, confirming the mechanism transfers across GPU architectures. All operators in the mlx-snn library are open source.

Related papers

• Dynamic Spectral Filtering for Temporal Graph Learning: Learning Evolving Propagation Operators [0.913755431537592]
  Temporal graph learning is commonly organized around the evolution of node states or the encoding of interaction histories.<n>We study underexplored, operator-centric question: should the graph propagation itself evolve over time?
  arXiv  Detail & Related papers  (2026-07-30T09:05:46Z)
• Training Non-Differentiable Networks via Optimal Transport [1.5229257192293202]
  PolyStep is a gradient-free method that updates parameters using only forward passes.<n>We train genuinely non-differentiable models where existing gradient-free methods collapse to near-random accuracy.<n>On hard-LIF spiking networks we reach 93.4% test accuracy, outperforming all gradient-free baselines by over 60pp and closing to within 4.4pp of a surrogate-gradient Adam ceiling.
  arXiv  Detail & Related papers  (2026-05-03T15:20:56Z)
• Pip-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching [2.226667542457085]
  We analyze iterative refinement and reveal that disparity updates are spatially sparse and temporally redundant.<n>We propose a collaborative monocular prior transfer framework that implicitly embeds depth priors without requiring a dedicated monocular encoder.<n>Third, we develop FlashGRU, a hardware-aware RNN operator leveraging structured sparsity and I/O-conscious design.
  arXiv  Detail & Related papers  (2026-02-24T02:51:37Z)
• Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks [87.16809558673403]
  Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure.<n>We study a timing-only adversary that retimes existing spikes while preserving spike counts and amplitudes in event-driven SNNs.
  arXiv  Detail & Related papers  (2026-02-03T09:06:53Z)
• LUT-Compiled Kolmogorov-Arnold Networks for Lightweight DoS Detection on IoT Edge Devices [20.271194684947282]
  Kolmogorov-Arnold Networks (KANs) offer a compact alternative to Multi-Layer Perceptrons (MLPs)<n>B-spline evaluation introduces significant computational overhead unsuitable for latency-critical IoT applications.<n>We propose a lookup table (LUT) compilation pipeline that replaces expensive spline computations with precomputed quantized tables.
  arXiv  Detail & Related papers  (2026-01-12T22:32:18Z)
• Speedy MASt3R [68.47052557089631]
  MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching scheme.<n>Fast MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy.<n>This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.
  arXiv  Detail & Related papers  (2025-03-13T03:56:22Z)
• Data-Free Dynamic Compression of CNNs for Tractable Efficiency [46.498278084317704]
  structured pruning approaches have shown promise in lowering floating-point operations without substantial drops in accuracy.<n>We propose HASTE (Hashing for Tractable Efficiency), a data-free, plug-and-play convolution module that instantly reduces a network's test-time inference cost without training or fine-tuning.<n>We demonstrate our approach on the popular vision benchmarks CIFAR-10 and ImageNet, where we achieve a 46.72% reduction in FLOPs with only a 1.25% loss in accuracy.
  arXiv  Detail & Related papers  (2023-09-29T13:09:40Z)
• Efficient Dataset Distillation Using Random Feature Approximation [109.07737733329019]
  We propose a novel algorithm that uses a random feature approximation (RFA) of the Neural Network Gaussian Process (NNGP) kernel. Our algorithm provides at least a 100-fold speedup over KIP and can run on a single GPU. Our new method, termed an RFA Distillation (RFAD), performs competitively with KIP and other dataset condensation algorithms in accuracy over a range of large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-21T15:56:13Z)
• Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns [77.34726150561087]
  We introduce four complicated missing patterns, including missing and three fiber-like missing cases according to the mode-drivenn fibers. Despite nonity of the objective function in our model, we derive the optimal solutions by integrating alternating data-mputation method of multipliers.
  arXiv  Detail & Related papers  (2022-05-19T08:37:56Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• Res-GCNN: A Lightweight Residual Graph Convolutional Neural Networks for Human Trajectory Forecasting [0.0]
  We propose a Residual Graph Convolutional Neural Network (Res-GCNN), which models the interactive behaviors of pedes-trians. Results show an improvement over the state of art by 13.3% on the Final Displacement Error (FDE) which reaches 0.65 meter. The code will be made publicly available on GitHub.
  arXiv  Detail & Related papers  (2020-11-18T11:18:16Z)
• RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices [57.877112704841366]
  This paper proposes RT3D, a model compression and mobile acceleration framework for 3D CNNs. For the first time, real-time execution of 3D CNNs is achieved on off-the-shelf mobiles.
  arXiv  Detail & Related papers  (2020-07-20T02:05:32Z)

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.