CogniSNN: A First Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Expandability and Neuroplasticity

2025-05-09 · Yongsheng Huang, Peibo Duan, Zhipeng Liu, Kai Sun, Changsheng Zhang, Bin Zhang, Mingkun Xu

Despite advances in spiking neural networks (SNNs) in numerous tasks, their architectures remain highly similar to traditional artificial neural networks (ANNs), restricting their ability to mimic natural connections between biological neurons. This paper develops a new modeling paradigm for SNN with random graph architecture (RGA), termed Cognition-aware SNN (CogniSNN). Furthermore, we improve the expandability and neuroplasticity of CogniSNN by introducing a modified spiking residual neural node (ResNode) to counteract network degradation in deeper graph pathways, as well as a critical path-based algorithm that enables CogniSNN to perform continual learning on new tasks leveraging the features of the data and the RGA learned in the old task. Experiments show that CogniSNN with re-designed ResNode performs outstandingly in neuromorphic datasets with fewer parameters, achieving 95.5% precision in the DVS-Gesture dataset with only 5 timesteps. The critical path-based approach decreases 3% to 5% forgetting while maintaining expected performance in learning new tasks that are similar to or distinct from the old ones. This study showcases the potential of RGA-based SNN and paves a new path for biologically inspired networks based on graph theory.

📄 PDF Abstract BibTeX arXiv:2505.05992

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

SNN Spiking Neural Networks (SNNs) are a class of artificial neural networks inspired by the structure and functioning of the brain's neural networks. Unlike traditional…

RGA In relation-aware global attention (RGA) stresses the importance of global structural information provided by pairwise relations, and uses it to produce attention maps. RGA…

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

2025-12-12 · Yongsheng Huang, Peibo Duan, Yujie Wu, Kai Sun 외 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 …

Learning-Guided Sparsification of Dynamic Graphs in Robotic Exploration

2026-04-15 · Adithya V. Sastry, Bibek Poudel, Weizi Li arxiv

Many robotic exploration algorithms rely on graph structures for frontier-based exploration and dynamic path planning. However, these graphs grow rapidly, accumulating redundant information and impacting performance. We …

Combinatorial Pure Exploration of Causal Bandits

2022-06-16 · Nuoya Xiong, Wei Chen

The combinatorial pure exploration of causal bandits is the following online learning task: given a causal graph with unknown causal inference distributions, in each round we choose a subset of variables to intervene or …

Causal Inference Multi-Armed Bandits

NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search

2020-03-28 · Chen Wei, Chuang Niu, Yiping Tang, Yue Wang 외

Neural architecture search (NAS) is a promising method for automatically design neural architectures. NAS adopts a search strategy to explore the predefined search space to find outstanding performance architecture with …

Bayesian Optimization Evolutionary Algorithms Neural Architecture Search

BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling

2022-03-21 · Cheng Wan, Youjie Li, Ang Li, Nam Sung Kim 외

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art method for graph-based learning tasks. However, training GCNs at scale is still challenging, hindering both the exploration of more sophisticated G…

Node Classification