mlsanityData to 14 Oct 2026

SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks

arXiv 2509.22581 ↗First posted 26 Sep 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based models remain underexplored compared to those for artificial neural networks (ANNs). In this paper, we introduce SpikeMatch, the first SSL framework for SNNs that leverages the temporal dynamics through the leakage factor of SNNs for diverse pseudo-labeling within a co-training framework. By utilizing agreement among multiple predictions from a single SNN, SpikeMatch generates reliable pseudo-labels from weakly-augmented unlabeled samples to train on strongly-augmented ones, effectively mitigating confirmation bias by capturing discriminative features with limited labels. Experiments show that SpikeMatch outperforms existing SSL methods adapted to SNN backbones across various standard benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

37 of 53 references.

References · 37

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2016Wide Residual Networkscited by 3,070
  3. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  6. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  7. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  8. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  9. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  10. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  11. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  12. 2020Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learningcited by 297
25 more
  1. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  2. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  3. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 198
  4. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  5. 2021AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptationcited by 104
  6. 2020DMT: Dynamic Mutual Training for Semi-Supervised Learningcited by 77
  7. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 65
  8. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  9. 2021Visual Explanations from Spiking Neural Networks using Interspike Intervalscited by 27
  10. 2023Diverse Cotraining Makes Strong Semi-Supervised Segmentorcited by 26
  11. 2023FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learningcited by 20
  12. 2020Towards Understanding the Effect of Leak in Spiking Neural Networkscited by 15
  13. 2021Semi-Supervised Learning with Multi-Head Co-Trainingcited by 15
  14. 2023JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classificationcited by 15
  15. 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspectivecited by 12
  16. 2023Boosting Semi-Supervised Learning by bridging high and low-confidence predictionscited by 11
  17. 2023Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Futurecited by 10
  18. 2023Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistencycited by 10
  19. 2023MarginMatch: Improving Semi-Supervised Learning with Pseudo-Marginscited by 10
  20. 2023SequenceMatch: Revisiting the design of weak-strong augmentations for Semi-supervised learningcited by 8
  21. 2017Theoretical Foundation of Co-Training and Disagreement-Based Algorithmscited by 6
  22. 2022On the Importance of Calibration in Semi-supervised Learningcited by 6
  23. 2024Towards Understanding Why FixMatch Generalizes Better Than Supervised Learningcited by 5
  24. 2024RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learningcited by 5
  25. 2021Semi-supervised learning combining backpropagation and STDP: STDP enhances learning by backpropagation with a small amount of labeled data in a spiking neural networkcited by 3

Built on by

Not cited yet.