mlsanityData to 14 Oct 2026

CogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural Networks

arXiv 2512.11743 ↗First posted 12 Dec 2025cs.NE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Spiking neural networks (SNNs), regarded as the third generation of artificial neural networks, are expected to bridge the gap between artificial intelligence and computational neuroscience. However, most mainstream SNN research directly adopts the rigid, chain-like hierarchical architecture of traditional artificial neural networks (ANNs), ignoring key structural characteristics of the brain. Biological neurons are stochastically interconnected, forming complex neural pathways that exhibit Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability. In this paper, we introduce a new SNN paradigm, named Cognition-aware SNN (CogniSNN), by incorporating Random Graph Architecture (RGA). Furthermore, we address the issues of network degradation and dimensional mismatch in deep pathways by introducing an improved pure spiking residual mechanism alongside an adaptive pooling strategy. Then, we design a Key Pathway-based Learning without Forgetting (KP-LwF) approach, which selectively reuses critical neural pathways while retaining historical knowledge, enabling efficient multi-task transfer. Finally, we propose a Dynamic Growth Learning (DGL) algorithm that allows neurons and synapses to grow dynamically along the internal temporal dimension. Extensive experiments demonstrate that CogniSNN achieves performance comparable to, or even surpassing, current state-of-the-art SNNs on neuromorphic datasets and Tiny-ImageNet. The Pathway-Reusability enhances the network's continuous learning capability across different scenarios, while the dynamic growth algorithm improves robustness against interference and mitigates the fixed-timestep constraints during neuromorphic chip deployment. This work demonstrates the potential of SNNs with random graph structures in advancing brain-inspired intelligence and lays the foundation for their practical application on neuromorphic hardware.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 53 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

21 of 53 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  3. 2016Learning without Forgettingcited by 2,496
  4. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  5. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  6. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
  7. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  8. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 271
  9. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  10. 2019Exploring Randomly Wired Neural Networks for Image Recognitioncited by 103
  11. 2020Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differencescited by 40
  12. 2023Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorizationcited by 35
9 more
  1. 2020Brain-inspired global-local learning incorporated with neuromorphic computingcited by 28
  2. 2021Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learningcited by 22
  3. 2024Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networkcited by 19
  4. 2024TIM: An Efficient Temporal Interaction Module for Spiking Transformercited by 12
  5. 2023Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagationcited by 10
  6. 2023Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networkscited by 7
  7. 2024Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networkscited by 2
  8. 2025Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deploymentcited by 2
  9. 2025Efficient Training of Spiking Neural Networks by Spike-aware Data Pruningcited by 1

Built on by

Not cited yet.