mlsanityData to 14 Oct 2026

Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation

arXiv 2205.00459 ↗First posted 1 May 2022cs.NE cs.LGcited by 89

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. However, it is a challenge to efficiently train SNNs due to their non-differentiability. Most existing methods either suffer from high latency (i.e., long simulation time steps), or cannot achieve as high performance as Artificial Neural Networks (ANNs). In this paper, we propose the Differentiation on Spike Representation (DSR) method, which could achieve high performance that is competitive to ANNs yet with low latency. First, we encode the spike trains into spike representation using (weighted) firing rate coding. Based on the spike representation, we systematically derive that the spiking dynamics with common neural models can be represented as some sub-differentiable mapping. With this viewpoint, our proposed DSR method trains SNNs through gradients of the mapping and avoids the common non-differentiability problem in SNN training. Then we analyze the error when representing the specific mapping with the forward computation of the SNN. To reduce such error, we propose to train the spike threshold in each layer, and to introduce a new hyperparameter for the neural models. With these components, the DSR method can achieve state-of-the-art SNN performance with low latency on both static and neuromorphic datasets, including CIFAR-10, CIFAR-100, ImageNet, and DVS-CIFAR10.

Key facts. Cited by 89 papers in the map (data through 14 Oct 2026). Builds on 34 of its 61 references that are in the map. First posted on arXiv 1 May 2022.

Builds on

34 of 61 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  6. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  7. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  8. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  9. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  10. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  11. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  12. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
22 more
  1. 2018Deep Learning in Spiking Neural Networkscited by 263
  2. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  3. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  4. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
  5. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 177
  6. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 145
  7. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 144
  8. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 139
  9. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 123
  10. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 117
  11. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 100
  12. 2021Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networkscited by 78
  13. 2016Supervised learning based on temporal coding in spiking neural networkscited by 76
  14. 2020DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscited by 71
  15. 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 70
  16. 2015Spiking Deep Networks with LIF Neuronscited by 63
  17. 2020Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networkscited by 59
  18. 2017Gradient Descent for Spiking Neural Networkscited by 48
  19. 2019Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performancecited by 46
  20. 2021Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium Statecited by 40
  21. 2018Spiking Deep Residual Networkcited by 21
  22. 2021Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networkscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 10; 2023: 25; 2024: 26; 2025: 23; 2026: 5.

89 papers.

Sort:

By area:

  1. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 271
  2. 2023Spike-driven Transformercited by 146
  3. 2024Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Trainingcited by 59
  4. 2022Online Training Through Time for Spiking Neural Networkscited by 49
  5. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
  6. 2023Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikescited by 40
  7. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 38
  8. 2023Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networkscited by 37
  9. 2022TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networkscited by 35
  10. 2023Direct Learning-Based Deep Spiking Neural Networks: A Reviewcited by 31
  11. 2024SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanismscited by 31
  12. 2024Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticketcited by 30
38 more
  1. 2023RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networkscited by 28
  2. 2023Training Full Spike Neural Networks via Auxiliary Accumulation Pathwaycited by 26
  3. 2022STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networkscited by 20
  4. 2022Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Networkcited by 19
  5. 2024Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networkcited by 19
  6. 2024Spiking Graph Neural Network on Riemannian Manifoldscited by 16
  7. 2024Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networkscited by 14
  8. 2024TIM: An Efficient Temporal Interaction Module for Spiking Transformercited by 12
  9. 2024Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithmscited by 12
  10. 2024LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Unitscited by 11
  11. 2023Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagationcited by 10
  12. 2024FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networkscited by 10
  13. 2022A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networkscited by 9
  14. 2024Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networkscited by 9
  15. 2023Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoffcited by 8
  16. 2023SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networkscited by 8
  17. 2023Tensor Decomposition Based Attention Module for Spiking Neural Networkscited by 8
  18. 2024Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networkscited by 8
  19. 2024Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagationcited by 8
  20. 2023S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networkscited by 7
  21. 2024EventRPG: Event Data Augmentation with Relevance Propagation Guidancecited by 7
  22. 2022Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networkscited by 6
  23. 2023AutoST: Training-free Neural Architecture Search for Spiking Transformerscited by 6
  24. 2023Memory-Efficient Reversible Spiking Neural Networkscited by 6
  25. 2024Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkcited by 6
  26. 2025Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacementcited by 6
  27. 2024FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversioncited by 5
  28. 2024Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoningcited by 5
  29. 2025Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexitycited by 5
  30. 2022Hoyer regularizer is all you need for ultra low-latency spiking neural networkscited by 4
  31. 2023Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognitioncited by 4
  32. 2025TESS: A Scalable Temporally and Spatially Local Learning Rule for Spiking Neural Networkscited by 4
  33. 2023Temporal Contrastive Learning for Spiking Neural Networkscited by 3
  34. 2023Attention-free Spikformer: Mixing Spike Sequences with Simple Linear Transformscited by 3
  35. 2023Spiking Neural Networks with Dynamic Time Steps for Vision Transformerscited by 3
  36. 2024SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognitioncited by 3
  37. 2024Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognitioncited by 3
  38. 2024Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networkscited by 3

50 most cited of 89 All 89 (JSON)