
SiGNN, a novel framework, effectively integrates the temporal dynamics of Spiking Neural Networks (SNNs) with the powerful capabilities of Graph Neural Networks (GNNs) to learn enhanced spatial-temporal node representations on dynamic graphs.


coremsg

signn-a-spike-induced-graph-neural-network-for-enhancing-dynamic-graph-representation-learning


SiGNN: A Spike-induced Graph Neural Network for Enhancing Dynamic Graph Representation Learning


title_rewrite


A novel recurrent learning framework named Recurrent Structure-reinforced Graph Transformer (RSGT) that explicitly models the temporal states of edges in dynamic graphs to enhance the learning of node representations.


recurrent-structure-reinforced-graph-transformer-for-dynamic-graph-representation-learning-with-explicit-modeling-of-edge-temporal-states


Recurrent Structure-reinforced Graph Transformer for Dynamic Graph Representation Learning with Explicit Modeling of Edge Temporal States
