Selective Activation via Neuronal Dynamics for Continual Learning in Spiking Neural Networks

Continual learning with Spiking Neural Networks (SNNs) offers a promising solution for low-power, rehearsal-free learning on resource-constrained devices. Brain-inspired selective activation, arising from neural competition and lateral inhibition, is crucial for learning sparse, task-specific representations. However, existing $k$-Winner-Take-All ($k$-WTA) SNNs allocate neurons statically, leaving many neurons inactive while task-relevant neurons remain vulnerable to subsequent interference. We propose STAR, a Spike-driven Task-Adaptive Resource allocation framework that manages the neuron lifecycle under a fixed capacity. During task training, Generate-and-Test (GnT) uses maturity-gated spike utility to replace low-utility neurons with mutated clones of high-utility neurons, thereby renewing plasticity. At task boundaries, Sleep Consolidation protects statistically selected experts and reinitializes redundant neurons to preserve knowledge and release capacity. Together, they form a generate–select–consolidate–release cycle without network expansion or data replay. Experiments on Split-MNIST, CIFAR-100, and TinyImageNet show that STAR consistently improves accuracy, memory retention, and neuron utilization. On Split-MNIST, STAR improves average accuracy by $6.03\%$ percentage points and increases neuron utilization from $9.4\%$ to $61.6\%$, while reducing forgetting across all three benchmarks. Ablation and neurodynamic analyses further validate the complementarity of GnT and Sleep Consolidation in addressing the stability–plasticity dilemma.