Guardado en:
Detalles Bibliográficos
Autores principales: Jahin, Md Abrar, Fuad, Taufikur Rahman, Pujara, Jay, Knoblock, Craig
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.01124
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918486569123840
author Jahin, Md Abrar
Fuad, Taufikur Rahman
Pujara, Jay
Knoblock, Craig
author_facet Jahin, Md Abrar
Fuad, Taufikur Rahman
Pujara, Jay
Knoblock, Craig
contents 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 $ρ<1$, and BIBO stability; interpretability analyses reveal heterogeneous temporal receptive fields and a learned primacy effect with $83-88$% sparsity.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01124
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs
Jahin, Md Abrar
Fuad, Taufikur Rahman
Pujara, Jay
Knoblock, Craig
Machine Learning
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 $ρ<1$, and BIBO stability; interpretability analyses reveal heterogeneous temporal receptive fields and a learned primacy effect with $83-88$% sparsity.
title ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs
topic Machine Learning
url https://arxiv.org/abs/2602.01124