ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs

TL;DR

ChronoSpike introduces an adaptive spiking graph neural network that combines local and global modeling techniques, achieving superior performance and efficiency on dynamic graph benchmarks.

Contribution

It integrates learnable LIF neurons, multi-head spatial attention, and a lightweight Transformer to enhance dynamic graph learning with theoretical guarantees.

Findings

Outperforms 12 state-of-the-art baselines by 2-2.4% in F1 scores.

Achieves 3-10x faster training than recurrent methods.

Maintains constant parameter budget regardless of graph size.

Abstract

Dynamic graph representation learning requires capturing both structural relations and temporal evolution, yet existing approaches face a core trade-off: attention-based methods offer expressiveness at $O(T^2)$ complexity, while recurrent architectures suffer from gradient pathologies and dense state storage. Spiking neural networks provide event-driven efficiency but are constrained by sequential propagation, binary information loss, and local aggregation that lacks global context. We propose ChronoSpike, an adaptive spiking graph neural network that integrates learnable LIF neurons with per-channel membrane dynamics, multi-head spatially-attentive aggregation over continuous features, and a lightweight Transformer temporal encoder. This design enables fine-grained local modeling and long-range dependency capture with $O(T \cdot d)$ activation/state memory and an additional $O(T^2)$ per-node attention term that remains small for the horizons evaluated here. ChronoSpike outperforms twelve state-of-the-art baselines on three large benchmarks by $2.0$% Macro-F1 and $2.4$% Micro-F1 on average while achieving $3-10\times$ faster training than recurrent methods with a constant 105K-parameter budget independent of graph size. We provide theoretical guarantees for membrane potential boundedness, gradient flow stability under contraction factor $\rho<1$, and BIBO stability; interpretability analyses reveal heterogeneous temporal receptive fields and a learned primacy effect with $83-88$% sparsity.