MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912967087357952 |
|---|---|
| author | Huang, Yongsheng Duan, Peibo Wu, Yujie Sun, Kai Liu, Zhipeng Liu, Jiaxiang Li, Guangyu Zhang, Changsheng Zhang, Bin Xu, Mingkun |
| author_facet | Huang, Yongsheng Duan, Peibo Wu, Yujie Sun, Kai Liu, Zhipeng Liu, Jiaxiang Li, Guangyu Zhang, Changsheng Zhang, Bin Xu, Mingkun |
| contents | Spiking Neural Networks (SNNs) currently face a critical bottleneck: while individual neurons exhibit dynamic biological properties, their macro-scopic architectures remain confined within conventional connectivity patterns that are static and hierarchical. This discrepancy between neuron-level dynamics and network-level fixed connectivity eliminates critical brain-like lateral interactions, limiting adaptability in changing environments. To address this, we propose MorphSNN, a backbone framework inspired by biological non-synaptic diffusion and structural plasticity. Specifically, we introduce a Graph Diffusion (GD)mechanism to facilitate efficient undirected signal propagation, complementing the feedforward hierarchy. Furthermore, it incorporates a Spatio-Temporal Structural Plasticity (STSP) mechanism, endowing the network with the capability for instance-specific, dynamic topological reorganization, thereby overcoming the limitations of fixed topologies. Experiments demonstrate that MorphSNN achieves state-of-the-art accuracy on static and neuromorphic datasets; for instance, it reaches 83.35% accuracy on N-Caltech101 with only 5 timesteps. More importantly, its self-evolving topology functions as an intrinsic distribution fingerprint, enabling superior Out-of- Distribution (OOD) detection without auxiliary training. The code is available at anonymous.4open.science/r/MorphSNN-B0BC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14285 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks Huang, Yongsheng Duan, Peibo Wu, Yujie Sun, Kai Liu, Zhipeng Liu, Jiaxiang Li, Guangyu Zhang, Changsheng Zhang, Bin Xu, Mingkun Neural and Evolutionary Computing Spiking Neural Networks (SNNs) currently face a critical bottleneck: while individual neurons exhibit dynamic biological properties, their macro-scopic architectures remain confined within conventional connectivity patterns that are static and hierarchical. This discrepancy between neuron-level dynamics and network-level fixed connectivity eliminates critical brain-like lateral interactions, limiting adaptability in changing environments. To address this, we propose MorphSNN, a backbone framework inspired by biological non-synaptic diffusion and structural plasticity. Specifically, we introduce a Graph Diffusion (GD)mechanism to facilitate efficient undirected signal propagation, complementing the feedforward hierarchy. Furthermore, it incorporates a Spatio-Temporal Structural Plasticity (STSP) mechanism, endowing the network with the capability for instance-specific, dynamic topological reorganization, thereby overcoming the limitations of fixed topologies. Experiments demonstrate that MorphSNN achieves state-of-the-art accuracy on static and neuromorphic datasets; for instance, it reaches 83.35% accuracy on N-Caltech101 with only 5 timesteps. More importantly, its self-evolving topology functions as an intrinsic distribution fingerprint, enabling superior Out-of- Distribution (OOD) detection without auxiliary training. The code is available at anonymous.4open.science/r/MorphSNN-B0BC. |
| title | MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2603.14285 |