ChronoSpike is a spiking GNN that integrates adaptive LIF neurons with spatial attention and temporal transformers to outperform baselines on dynamic graph benchmarks by 2% F1 while training 3-10x faster with fixed parameters and stability guarantees.
Each neuron i maintains a membrane potential u(t) i governed by learnable time constants τi and thresholds Vth,i, enabling heterogeneous temporal dynamics across feature channels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs
ChronoSpike is a spiking GNN that integrates adaptive LIF neurons with spatial attention and temporal transformers to outperform baselines on dynamic graph benchmarks by 2% F1 while training 3-10x faster with fixed parameters and stability guarantees.