Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation
This work addresses efficiency challenges for deploying spiking Transformers in resource-constrained environments, representing an incremental improvement through hybrid methods.
The paper tackled the high parameter and computational costs of spiking Transformer models by combining synapse pruning with a synergistic learning-based compensation strategy, resulting in significantly reduced model size and computational overhead while maintaining competitive performance on benchmark datasets.
As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer~(ST)-based models require a substantial number of parameters and incur high computational costs, thus limiting their deployment in resource-constrained environments. To address these challenges, we propose combining synapse pruning with a synergistic learning-based compensation strategy to derive lightweight ST-based models. Specifically, two types of tailored pruning strategies are introduced to reduce redundancy in the weight matrices of ST blocks: an unstructured $\mathrm{L_{1}P}$ method to induce sparse representations, and a structured DSP method to induce low-rank representations. In addition, we propose an enhanced spiking neuron model, termed the synergistic leaky integrate-and-fire (sLIF) neuron, to effectively compensate for model pruning through synergistic learning between synaptic and intrinsic plasticity mechanisms. Extensive experiments on benchmark datasets demonstrate that the proposed methods significantly reduce model size and computational overhead while maintaining competitive performance. These results validate the effectiveness of the proposed pruning and compensation strategies in constructing efficient and high-performing ST-based models.