MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks
This addresses a critical limitation in SNNs for neuromorphic computing by enabling dynamic, brain-like interactions, though it is an incremental improvement over existing SNN methods.
The paper tackles the bottleneck of static connectivity in Spiking Neural Networks (SNNs) by proposing MorphSNN, which introduces adaptive graph diffusion and structural plasticity, achieving state-of-the-art accuracy of 83.35% on N-Caltech101 with 5 timesteps and enabling superior out-of-distribution detection.
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.