# SpikeSTAG: Spatial-Temporal Forecasting via GNN-SNN Collaboration

arXiv: https://arxiv.org/abs/2508.02069 · HTML: https://mlsanity.com/paper/2508.02069/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https://mlsanity.com/paper/2103.07719/) (2021)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [AliGraph: A Comprehensive Graph Neural Network Platform](https://mlsanity.com/paper/1902.08730/) (2019)
- [FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective](https://mlsanity.com/paper/2311.06190/) (2023)
- [Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks](https://mlsanity.com/paper/2105.11654/) (2021)
- [PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest](https://mlsanity.com/paper/2007.03634/) (2020)
- [Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks](https://mlsanity.com/paper/2208.10364/) (2022)
- [Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning](https://mlsanity.com/paper/2107.06865/) (2021)
- [SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models](https://mlsanity.com/paper/2408.14909/) (2024)
- [STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks](https://mlsanity.com/paper/2503.02689/) (2025)
- [SpikE: spike-based embeddings for multi-relational graph data](https://mlsanity.com/paper/2104.13398/) (2021)
- [Learning through structure: towards deep neuromorphic knowledge graph embeddings](https://mlsanity.com/paper/2109.10376/) (2021)
- [TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting](https://mlsanity.com/paper/2503.05108/) (2025)
- [Multivariate Time Series Classification Using Spiking Neural Networks](https://mlsanity.com/paper/2007.03547/) (2020)
- [Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks](https://mlsanity.com/paper/2110.02865/) (2021)
- [SpikeGraphormer: A High-Performance Graph Transformer with Spiking Graph Attention](https://mlsanity.com/paper/2403.15480/) (2024)
- [Unleashing the Potential of Spiking Neural Networks for Sequential Modeling with Contextual Embedding](https://mlsanity.com/paper/2308.15150/) (2023)

## Built on by (most cited first, 3 of 3)

- [SpikySpace: A Spiking State Space Model for Energy-Efficient Time Series Forecasting](https://mlsanity.com/paper/2601.02411/) (2026)
- [Long-Horizon Traffic Forecasting via Incident-Aware Conformal Spatio-Temporal Transformers](https://mlsanity.com/paper/2603.16857/) (2026)
- [SpikeLite: Lightweight Spiking Neural Networks for Time-Series Forecasting](https://mlsanity.com/paper/2609.35097/) (2026)

## Abstract (arXiv)

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.