Neural Acceleration for Graph Partitioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Booth, Joshua Dennis, Patel, Vishvam
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918515591610368
author Booth, Joshua Dennis
Patel, Vishvam
author_facet Booth, Joshua Dennis
Patel, Vishvam
contents Graph Partitioning is a critical problem in numerous scientific and engineering domains including social network analysis, VLSI design, and many more. Spectral methods are known to produce quality partitions while minimizing edge cuts for a wide range of problems. However, the computational cost associated with the calculation of the Fiedler vector, an eigenvector associated with the second smallest eigenvalue of the graph Laplacian, remains a significant bottleneck due to memory issues and computational costs. In this paper, we present an accelerated approach to spectral bisection partitioning by replacing the traditional eigenvalue calculation with a simple artificial neural network model to approximate the Fiedler vector. We demonstrate that our approach achieves partitioning quality comparable to spectral bisection while significantly reducing the computational overhead, making it more scalable and efficient for large-scale problems
format Preprint
id arxiv_https___arxiv_org_abs_2605_21519
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Acceleration for Graph Partitioning
Booth, Joshua Dennis
Patel, Vishvam
Social and Information Networks
Machine Learning
Graph Partitioning is a critical problem in numerous scientific and engineering domains including social network analysis, VLSI design, and many more. Spectral methods are known to produce quality partitions while minimizing edge cuts for a wide range of problems. However, the computational cost associated with the calculation of the Fiedler vector, an eigenvector associated with the second smallest eigenvalue of the graph Laplacian, remains a significant bottleneck due to memory issues and computational costs. In this paper, we present an accelerated approach to spectral bisection partitioning by replacing the traditional eigenvalue calculation with a simple artificial neural network model to approximate the Fiedler vector. We demonstrate that our approach achieves partitioning quality comparable to spectral bisection while significantly reducing the computational overhead, making it more scalable and efficient for large-scale problems
title Neural Acceleration for Graph Partitioning
topic Social and Information Networks
Machine Learning
url https://arxiv.org/abs/2605.21519