SpikySpace: A Spiking State Space Model for Energy-Efficient Time Series Forecasting
This work addresses energy-efficient forecasting for domains like traffic management and industrial monitoring, representing an incremental improvement by combining spiking neural networks with state-space models.
The authors tackled the problem of energy-efficient time-series forecasting for edge devices by proposing SpikySpace, a spiking state-space model that reduces computational costs; it achieved up to 3.0% higher accuracy and over 96.1% lower energy consumption compared to leading SNN methods.
Time-series forecasting in domains like traffic management and industrial monitoring often requires real-time, energy-efficient processing on edge devices with limited resources. Spiking neural networks (SNNs) offer event-driven computation and ultra-low power and have been proposed for use in this space. Unfortunately, existing SNN-based time-series forecasters often use complex transformer blocks. To address this issue, we propose SpikySpace, a spiking state-space model (SSM) that reduces the quadratic cost in the attention block to linear time via spiking selective scanning. Further, we introduce PTsoftplus and PTSiLU, two efficient approximations of SiLU and Softplus that replace costly exponential and division operations with simple bit-shifts. Evaluated on four multivariate time-series benchmarks, SpikySpace outperforms the leading SNN in terms of accuracy by up to 3.0% while reducing energy consumption by over 96.1%. As the first fully spiking state-space model, SpikySpace bridges neuromorphic efficiency with modern sequence modeling, opening a practical path toward efficient time series forecasting systems. Our code is available at https://anonymous.4open.science/r/SpikySpace.