mlsanityData to 14 Oct 2026

SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning

arXiv 2507.02945 ↗First posted 28 Jun 2025cs.NE cs.AI cs.LGcited by 0

On the map: Deep reinforcement learning methods → Spiking and neuromorphic RL

Abstract (arXiv)

While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and synaptic operations (SynOps) to facilitate the edge deployment of SNNs, among which search-based pruning methods search for the SNNs structure after pruning. However, existing search-based methods fail to directly use SynOps as the constraint because it will dynamically change in the searching process, resulting in the final searched network violating the expected SynOps target. In this paper, we introduce a novel SNN pruning framework called SPEAR, which leverages reinforcement learning (RL) technique to directly use SynOps as the searching constraint. To avoid the violation of SynOps requirements, we first propose a SynOps prediction mechanism called LRE to accurately predict the final SynOps after search. Observing SynOps cannot be explicitly calculated and added to constrain the action in RL, we propose a novel reward called TAR to stabilize the searching. Extensive experiments show that our SPEAR framework can effectively compress SNN under specific SynOps constraint.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spiking and neuromorphic RL, one of 15 directions in Deep reinforcement learning methods. Builds on 37 of its 62 references that are in the map. First posted on arXiv 28 Jun 2025.

Builds on

37 of 62 references.

References · 37

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  4. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  5. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  6. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 378
  7. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  8. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  9. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  10. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 198
  11. 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 169
  12. 2023Spike-driven Transformercited by 146
25 more
  1. 2020A Survey on Evolutionary Neural Architecture Searchcited by 142
  2. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  3. 2022Attention Spiking Neural Networkscited by 107
  4. 2021Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationcited by 106
  5. 2024Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detectioncited by 67
  6. 2022GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 63
  7. 2024Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Trainingcited by 59
  8. 2022Neural Architecture Search for Spiking Neural Networkscited by 53
  9. 2021Pruning of Deep Spiking Neural Networks through Gradient Rewiringcited by 43
  10. 2022AutoSNN: Towards Energy-Efficient Spiking Neural Networkscited by 40
  11. 2023RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networkscited by 28
  12. 2023Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networkscited by 26
  13. 2024Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methodscited by 25
  14. 2021Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networkscited by 21
  15. 2024CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 21
  16. 2024Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentationcited by 19
  17. 2023Workload-Balanced Pruning for Sparse Spiking Neural Networkscited by 15
  18. 2018A Low Effort Approach to Structured CNN Design Using PCAcited by 14
  19. 2023A Unified Framework for Soft Threshold Pruningcited by 12
  20. 2024Efficient 3D Recognition with Event-driven Spike Sparse Convolutioncited by 11
  21. 2024Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruningcited by 10
  22. 2022Adaptive Sparse Structure Development with Pruning and Regeneration for Spiking Neural Networkscited by 9
  23. 2024Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignmentcited by 9
  24. 2024RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Accelerationcited by 9
  25. 2024LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimizationcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026BASC : Behavior-Aligned Quantization and Pruning for Low-Bit Spiking Neural Networks
  2. 2026TP-Spikformer: Token Pruned Spiking Transformer
  3. 2024GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL
  4. 2025QP-SNN: Quantized and Pruned Spiking Neural Networks
  5. 2025Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
  6. 2025SpikeRL: A Scalable and Energy-efficient Framework for Deep Spiking Reinforcement Learning
  7. 2023The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networks
  8. 2025Spatio-Temporal Pruning for Compressed Spiking Large Language Models