A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinations

DOI10.1137/21M1395351zbMath1485.05167arXiv2101.07730OpenAlexW3121197195MaRDI QIDQ5065464

Junteng Jia, Austin R. Benson

Publication date: 21 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2101.07730

zbMATH Keywords

network sciencesemi-supervised learninglabel propagationgraph learninggraph neural networksgraph convolutions

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Social networks; opinion dynamics (91D30) Artificial neural networks and deep learning (68T07) Small world graphs, complex networks (graph-theoretic aspects) (05C82) Learning and adaptive systems in artificial intelligence (68T05) Graph labelling (graceful graphs, bandwidth, etc.) (05C78) Graph algorithms (graph-theoretic aspects) (05C85)

Uses Software

• PMTK
• NetKit
• PairNorm
• GMNN
• SIGN

Cites Work

• Identification of peer effects through social networks
• Empirical stationary correlations for semi-supervised learning on graphs
• Prediction models for network-linked data
• Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix
• Statistical mechanics of complex networks
• Fast Estimation of $tr(f(A))$ via Stochastic Lanczos Quadrature
• Multi-Scale attributed node embedding
• Collective dynamics of ‘small-world’ networks
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinations