Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

global structural information

Global structural information refers to the overarching topological properties, connectivity patterns, and long-range relationships that characterize an entire network or graph beyond the immediate neighborhood of individual nodes. While local structural information captures direct connections between adjacent vertices, global structural information encompasses higher-order proximities, multi-hop pathways, community architectures, and macroscopic network organization. In computational network analysis and graph representation learning, incorporating global structural information enables models to encode how nodes fit into the broader system, preserving both broad contextual roles and distant relational dependencies when mapping graph topologies into lower-dimensional feature spaces.

1 item

GraRep: Learning Graph Representations with Global Structural Information

GraRep: Learning Graph Representations with Global Structural Information

Shaosheng Cao, Wei Lu, Qiongkai Xu

OrganizationsAustralian National UniversityIBMSingapore University of Technology and DesignXidian University

Why you should read this

Proposes GraRep, a graph representation learning model that captures high-order relational information by directly factorizing distinct k-step probability transition matrices to preserve global graph structure across separate subspaces without sampling.

In this paper, we present GraRep, a novel model for learning vertex representations of weighted graphs. This model learns low dimensional vectors to represent vertices appearing in a graph and, unlike existing work, integrates global structural information of the graph into the learning process. We also formally analyze the connections between our work and several previous research efforts, including the DeepWalk model of Perozzi et al. [20] as well as the skip-gram model with negative sampling of Mikolov et al. [18] We conduct experiments on a language network, a social network as well as a citation network and show that our learned global representations can be effectively used as features in tasks such as clustering, classification and visualization. Empirical results demonstrate that our representation significantly outperforms other state-of-the-art methods in such tasks.

Added

2026-09-24