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

keyword

large-scale information network

A large-scale information network is an expansive graph-based data structure used to represent complex relational systems, where nodes correspond to distinct entities and edges denote the interactions or relationships connecting them. Spanning massive numbers of elements across domains such as social media, academic citations, language co-occurrences, and the World Wide Web, these networks are typically characterized by high sparsity, weighted or directed connections, and power-law degree distributions. Because their sheer volume and structural complexity pose significant computational challenges for conventional algorithms, analyzing large-scale information networks requires scalable methods such as graph representation learning and distributed processing to support downstream applications like entity classification, link prediction, and community detection.

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