LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning

arXiv:2401.11772v2 Announce Type: replace
Abstract: Most existing graph neural networks (GNNs) are limited to undirected graphs, whose restricted scope of the captured relational information hinders their expressive capabilities and deployments in real-world scenarios. Compared with undirected graphs, directed graphs (digraphs) fit the demand for modeling more complex topological systems by capturing more intricate relationships between nodes, such as formulating transportation and financial networks. While some directed GNNs have been introduced, their inspiration mainly comes from deep learning architectures, which lead …

abstract arxiv capabilities cs.ai cs.lg cs.si demand deployments gnns graph graph neural networks graphs information modeling networks neural networks relational representation representation learning scale simple systems type world