A survey of dynamic graph neural networks

arXiv:2404.18211v1 Announce Type: new
Abstract: Graph neural networks (GNNs) have emerged as a powerful tool for effectively mining and learning from graph-structured data, with applications spanning numerous domains. However, most research focuses on static graphs, neglecting the dynamic nature of real-world networks where topologies and attributes evolve over time. By integrating sequence modeling modules into traditional GNN architectures, dynamic GNNs aim to bridge this gap, capturing the inherent temporal dependencies of dynamic graphs for a more authentic depiction of complex …

abstract applications arxiv cs.lg data domains dynamic gnns graph graph neural networks graphs however mining modeling nature networks neural networks research structured data survey tool type world