arXiv：cs.LG· Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara, Craig Knoblock·· 5 小时前AI 评分33
ChronoSpike：面向动态图的自适应脉冲图神经网络
ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs
AI 导读
ChronoSpike 是一种自适应脉冲图神经网络，结合可学习 LIF 神经元、多头空间注意力聚合与轻量 Transformer 时序编码器，在三个大型基准上平均超越十二个 SOTA 基线 2.0% Macro-F1 和 2.4% Micro-F1，训练速度比循环方法快 3-10 倍，参数量恒为 105K 且与图规模无关。
正文
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.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 \r{ho}<1, and BIBO stability; interpretability analyses reveal heterogeneous temporal receptive fields and a learned primacy effect with 83-88% sparsity. Our code is publicly available at: this https URL
| Comments: | Accepted at the Fifth Learning on Graphs Conference (LoG 2026) |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2602.01124 [cs.LG] |
| (or arXiv:2602.01124v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.01124 arXiv-issued DOI via DataCite |
Submission history
From: Taufikur Rahman Fuad [view email]
[v1]
Sun, 1 Feb 2026 09:50:21 UTC (664 KB)
[v2]
Fri, 3 Apr 2026 02:14:07 UTC (656 KB)
[v3]
Thu, 7 May 2026 09:19:58 UTC (649 KB)
[v4]
Fri, 2 Oct 2026 08:33:11 UTC (1,121 KB)
来源：arXiv：cs.LG · arxiv.org