SpikeLite：用于时间序列预测的轻量级脉冲神经网络

中文摘要 AI 辅助

脉冲神经网络（SNN）通过脉冲驱动计算为时间序列预测提供了一种节能范式。然而，近期基于SNN的预测器往往通过日益复杂的注意力机制或专门的神经元动力学来追求更高的精度，这削弱了SNN的轻量级动机。我们提出了SpikeLite，一个围绕两个模块构建的脉冲预测框架：用于频率敏感时间编码的频率选择性脉冲编码器（FSSE）和用于选择性跨通道交互的稀疏脉冲通道注意力（SSCA）模块。FSSE利用LIF动力学的低通滤波行为将每个输入序列重组为频率敏感组件，同时在分解阶段整体保留输入。随后，SSCA从编码的通道表示中学习一个二值掩码，并使用它在脉冲驱动的自注意力中选择性交换信息，保留信息丰富的跨通道交互，同时抑制冗余交互。当显式通道交互不必要时，SpikeLite使用更轻的仅FSSE的通道独立路径。在SeqSNN和SpikF协议下的实验覆盖了四个标准多变量和八个长期预测基准。SpikeLite在两种协议下均实现了最佳总体性能，平均$R^2$为0.790，RSE为0.440，在长期预测中平均MSE/MAE最低，为0.343/0.345。此外，在ECL数据集上的评估表明，SpikeLite实现了最低的报告能耗，进一步展示了其在节能时间序列预测方面的潜力。

英文摘要

Spiking neural networks (SNNs) offer an energy-efficient paradigm for time-series forecasting through spike-driven computation. However, recent SNN forecasters often pursue higher accuracy through increasingly complex attention mechanisms, or specialized neuronal dynamics, weakening the lightweight motivation of SNNs. We introduce SpikeLite, a spiking forecasting framework built around two modules: a Frequency-Selective Spiking Encoder (FSSE) for frequency-sensitive temporal encoding and a Sparse Spiking Channel Attention (SSCA) module for selective cross-channel interaction. FSSE exploits the low-pass filtering behavior of LIF dynamics to reorganize each input sequence into frequency-sensitive components while collectively preserving the input at the decomposition stage. SSCA then learns a binary mask from encoded channel representations and uses it to selectively exchange information within spike-driven self-attention, retaining informative cross-channel interactions while suppressing redundant ones. When explicit channel interaction is unnecessary, SpikeLite uses the lighter FSSE-only channel-independent path. Experiments under the SeqSNN and SpikF protocols cover four standard multivariate and eight long-term forecasting benchmarks. SpikeLite achieves the best aggregate performance under both protocols, with an average $R^2$ of 0.790 and RSE of 0.440, and lowest average MSE/MAE of 0.343/0.345 in long-term forecasting. Moreover, evaluation on the ECL dataset shows that SpikeLite achieves the lowest reported energy consumption, further demonstrating its potential for energy-efficient time-series forecasting.

发表机构

• Fudan University（复旦大学）

机构由 AI 辅助整理，请以论文原文为准。