Spiking Neural Networks (SNNs) have emerged as an energy-efficient alternative to conventional neural networks, demonstrating strong performance in computer vision and robotics. More recently, SNNs have been applied to time series forecasting (TSF), with methods exploring spiking temporal backbones, spike-compatible positional encodings, Fourier-domain processing, and redesigned neuron dynamics. However, existing SNN forecasting approaches process variables independently, lacking explicit mechanisms for modeling inter-variable dependencies. This is a critical limitation in multivariate settings, where cross-variable correlations carry substantial predictive information. We propose Spiking Fourier Graph Operators (SpikF-GO), which addresses this gap by combining a hypervariate graph formulation in which every scalar observation becomes a graph node with spike-driven spectral processing. SpikF-GO introduces a Hard Concrete frequency gate for learnable sparse frequency selection and a Complex LIF gate that applies independent spiking neurons to real and imaginary Fourier components, preserving binary, event-driven computation throughout the spectral domain. We further present a variant incorporating Central Pattern Generator-based positional encodings for stronger long-range temporal modeling. Evaluated on eight benchmarks under a unified experimental protocol, SpikF-GO achieves the best average rank among all SNN methods and outperforms its ANN counterpart, FourierGNN, at reduced energy cost. SpikF-GO maintains competitive accuracy even at substantially smaller embedding dimensions, thereby achieving significant energy reductions. To our knowledge, this is among the first works to bring graph-based multivariate modeling into the spiking domain for TSF and the first to provide a unified comparison across SNN forecasting architectures under a common experimental protocol.

翻译：脉冲神经网络（SNN）作为传统神经网络的一种高能效替代方案，已在计算机视觉和机器人领域展现出卓越性能。近年来，SNN被应用于时间序列预测（TSF），相关方法涉及脉冲时间骨干网络、尖峰兼容位置编码、频域处理及神经元动力学重构等方向。然而，现有SNN预测方法独立处理各变量，缺乏建模变量间依赖关系的显式机制。在多元场景中，跨变量相关性承载着显著预测信息，这一局限性尤为关键。我们提出脉冲傅里叶图算子（SpikF-GO），通过融合超变量图结构与脉冲驱动谱域处理解决该问题——该框架将每个标量观测值定义为图节点。SpikF-GO创新性地引入可学习稀疏频率选择的硬混凝土频率门控，以及独立作用于实部/虚部分量的复数LIF门控，在保持二进制事件驱动计算特性的同时实现频谱域处理。我们进一步提出基于中心模式生成器的位置编码变体，以增强长程时序建模能力。在统一实验协议下的八项基准测试中，SpikF-GO在SNN方法中取得最佳平均排名，并以更低能耗超越其ANN对应模型FourierGNN。即便采用显著缩小的嵌入维度，SpikF-GO仍保持竞争性精度，从而实现显著的能耗降低。据我们所知，这是首个将图基多元建模引入SNN领域用于TSF的研究，也是首个在统一实验框架下进行SNN预测架构横向对比的工作。