Faster Graph Embeddings via Coarsening

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fahrbach, Matthew, Goranci, Gramoz, Peng, Richard, Sachdeva, Sushant, Wang, Chi
Formato: Preprint
Publicado: 2020
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909225572106240
author Fahrbach, Matthew
Goranci, Gramoz
Peng, Richard
Sachdeva, Sushant
Wang, Chi
author_facet Fahrbach, Matthew
Goranci, Gramoz
Peng, Richard
Sachdeva, Sushant
Wang, Chi
contents Graph embeddings are a ubiquitous tool for machine learning tasks, such as node classification and link prediction, on graph-structured data. However, computing the embeddings for large-scale graphs is prohibitively inefficient even if we are interested only in a small subset of relevant vertices. To address this, we present an efficient graph coarsening approach, based on Schur complements, for computing the embedding of the relevant vertices. We prove that these embeddings are preserved exactly by the Schur complement graph that is obtained via Gaussian elimination on the non-relevant vertices. As computing Schur complements is expensive, we give a nearly-linear time algorithm that generates a coarsened graph on the relevant vertices that provably matches the Schur complement in expectation in each iteration. Our experiments involving prediction tasks on graphs demonstrate that computing embeddings on the coarsened graph, rather than the entire graph, leads to significant time savings without sacrificing accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2007_02817
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Faster Graph Embeddings via Coarsening
Fahrbach, Matthew
Goranci, Gramoz
Peng, Richard
Sachdeva, Sushant
Wang, Chi
Machine Learning
Data Structures and Algorithms
Graph embeddings are a ubiquitous tool for machine learning tasks, such as node classification and link prediction, on graph-structured data. However, computing the embeddings for large-scale graphs is prohibitively inefficient even if we are interested only in a small subset of relevant vertices. To address this, we present an efficient graph coarsening approach, based on Schur complements, for computing the embedding of the relevant vertices. We prove that these embeddings are preserved exactly by the Schur complement graph that is obtained via Gaussian elimination on the non-relevant vertices. As computing Schur complements is expensive, we give a nearly-linear time algorithm that generates a coarsened graph on the relevant vertices that provably matches the Schur complement in expectation in each iteration. Our experiments involving prediction tasks on graphs demonstrate that computing embeddings on the coarsened graph, rather than the entire graph, leads to significant time savings without sacrificing accuracy.
title Faster Graph Embeddings via Coarsening
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2007.02817