Guardado en:
Detalles Bibliográficos
Autor principal: Sahu, Subhajit
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.11415
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912443289042944
author Sahu, Subhajit
author_facet Sahu, Subhajit
contents Link prediction can help rectify inaccuracies in various graph algorithms, stemming from unaccounted-for or overlooked links within networks. However, many existing works use a baseline approach, which incurs unnecessary computational costs due to its high time complexity. Further, many studies focus on smaller graphs, which can lead to misleading conclusions. Here, we study the prediction of links using neighborhood-based similarity measures on large graphs. In particular, we improve upon the baseline approach (IBase), and propose a heuristic approach that additionally disregards large hubs (DLH), based on the idea that high-degree nodes contribute little similarity among their neighbors. On a server equipped with dual 16-core Intel Xeon Gold 6226R processors, DLH is on average 1019x faster than IBase, especially on web graphs and social networks, while maintaining similar prediction accuracy. Notably, DLH achieves a link prediction rate of 38.1M edges/s and improves performance by 1.6x for every doubling of threads.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11415
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Fast Parallel Approach for Neighborhood-based Link Prediction by Disregarding Large Hubs
Sahu, Subhajit
Social and Information Networks
Distributed, Parallel, and Cluster Computing
G.2.2; I.5.3
Link prediction can help rectify inaccuracies in various graph algorithms, stemming from unaccounted-for or overlooked links within networks. However, many existing works use a baseline approach, which incurs unnecessary computational costs due to its high time complexity. Further, many studies focus on smaller graphs, which can lead to misleading conclusions. Here, we study the prediction of links using neighborhood-based similarity measures on large graphs. In particular, we improve upon the baseline approach (IBase), and propose a heuristic approach that additionally disregards large hubs (DLH), based on the idea that high-degree nodes contribute little similarity among their neighbors. On a server equipped with dual 16-core Intel Xeon Gold 6226R processors, DLH is on average 1019x faster than IBase, especially on web graphs and social networks, while maintaining similar prediction accuracy. Notably, DLH achieves a link prediction rate of 38.1M edges/s and improves performance by 1.6x for every doubling of threads.
title A Fast Parallel Approach for Neighborhood-based Link Prediction by Disregarding Large Hubs
topic Social and Information Networks
Distributed, Parallel, and Cluster Computing
G.2.2; I.5.3
url https://arxiv.org/abs/2401.11415