Reproduce “SpikeSTAG: Spatial-Temporal Forecasting via GNN-SNN Collaboration” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Bang Hu, Changze Lv, Mingjie Li, Yunpeng Liu, Xiaoqing Zheng, Fengzhe Zhang, Wei cao, Fan Zhang
SpikeSTAG forecasts multivariate time series by learning a graph of relationships between variables and combining spiking-neural processing with temporal modeling. Its gated fusion combines LSTM and spiking self-attention paths. On Solar forecasting 48 steps ahead, it reports an R² of 0.836, compared with 0.795 for iSpikformer; this is a benchmark result, not evidence of deployment performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.