adaptive-graph-diffusion-and-structural-plasticity

---
name: adaptive-graph-diffusion-and-structural-plasticity
description: "Spiking Neural Networks (SNNs) currently face a critical bottleneck: while individual neurons exhibit dynamic biological properties, their macro-scopic architectures remain confined within conventiona..."
version: 1.0.0
author: Research Synthesis
license: MIT
metadata:
  hermes:
    tags: [neuroscience, research, arxiv]
    source_paper: "MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks (arXiv:2603.14285v1)"
    published: "2026-03-15"
    relevance_score: 18
---

# MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks

## Overview
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.

## Authors
Yongsheng Huang, Peibo Duan, Yujie Wu, Kai Sun, Zhipeng Liu, Jiaxiang Liu, Guangyu Li, Changsheng Zhang, Bin Zhang, Mingkun Xu

## Publication Information
- **arXiv ID**: 2603.14285v1
- **Published**: 2026-03-15
- **Category**: synaptic plasticity

## Key Insights
- Research focuses on advancing understanding in synaptic plasticity
- Relevance score: 18/20

## Links
- arXiv Abstract: https://arxiv.org/abs/2603.14285v1
- arXiv PDF: https://arxiv.org/pdf/2603.14285v1

## References
Yongsheng Huang, Peibo Duan, Yujie Wu, Kai Sun, Zhipeng Liu, Jiaxiang Liu, Guangyu Li, Changsheng Zhang, Bin Zhang, Mingkun Xu. "MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks". arXiv:2603.14285v1, 2026-03-15.