SpikeSTAG: Spatial-Temporal Forecasting via GNN-SNN Collaboration

TL;DR

SpikeSTAG introduces a novel SNN architecture that combines graph learning and spike-based temporal processing, significantly improving multivariate time-series forecasting accuracy, especially for long sequences, by integrating spatial and temporal features efficiently.

Contribution

This work pioneers the integration of graph structural learning with spiking neural networks for spatial-temporal forecasting, eliminating the need for predefined graphs and floating-point operations.

Findings

Outperforms state-of-the-art SNN models on all datasets.

Surpasses traditional models at long forecasting horizons.

Efficiently captures spatial-temporal dependencies without floating-point computations.

Abstract

Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, offer a distinctive approach for capturing the complexities of temporal data. However, their potential for spatial modeling in multivariate time-series forecasting remains largely unexplored. To bridge this gap, we introduce a brand new SNN architecture, which is among the first to seamlessly integrate graph structural learning with spike-based temporal processing for multivariate time-series forecasting. Specifically, we first embed time features and an adaptive matrix, eliminating the need for predefined graph structures. We then further learn sequence features through the Observation (OBS) Block. Building upon this, our Multi-Scale Spike Aggregation (MSSA) hierarchically aggregates neighborhood information through spiking SAGE layers, enabling multi-hop feature extraction while eliminating the need for floating-point operations. Finally, we propose a Dual-Path Spike Fusion (DSF) Block to integrate spatial graph features and temporal dynamics via a spike-gated mechanism, combining LSTM-processed sequences with spiking self-attention outputs, effectively improve the model accuracy of long sequence datasets. Experiments show that our model surpasses the state-of-the-art SNN-based iSpikformer on all datasets and outperforms traditional temporal models at long horizons, thereby establishing a new paradigm for efficient spatial-temporal modeling.