Deep Learning and Spectral Embedding for Graph Partitioning

10/16/2021
by   Alice Gatti, et al.
0

We present a graph bisection and partitioning algorithm based on graph neural networks. For each node in the graph, the network outputs probabilities for each of the partitions. The graph neural network consists of two modules: an embedding phase and a partitioning phase. The embedding phase is trained first by minimizing a loss function inspired by spectral graph theory. The partitioning module is trained through a loss function that corresponds to the expected value of the normalized cut. Both parts of the neural network rely on SAGE convolutional layers and graph coarsening using heavy edge matching. The multilevel structure of the neural network is inspired by the multigrid algorithm. Our approach generalizes very well to bigger graphs and has partition quality comparable to METIS, Scotch and spectral partitioning, with shorter runtime compared to METIS and spectral partitioning.

READ FULL TEXT
research
03/02/2019

GAP: Generalizable Approximate Graph Partitioning Framework

Graph partitioning is the problem of dividing the nodes of a graph into ...
research
07/22/2023

Spectral Normalized-Cut Graph Partitioning with Fairness Constraints

Normalized-cut graph partitioning aims to divide the set of nodes in a g...
research
04/08/2021

Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning

We present a novel method for graph partitioning, based on reinforcement...
research
10/29/2020

AutoAtlas: Neural Network for 3D Unsupervised Partitioning and Representation Learning

We present a novel neural network architecture called AutoAtlas for full...
research
01/20/2020

2PS: High-Quality Edge Partitioning with Two-Phase Streaming

Graph partitioning is an important preprocessing step to distributed gra...
research
03/02/2023

Distributed Deep Multilevel Graph Partitioning

We describe the engineering of the distributed-memory multilevel graph p...
research
09/12/2013

Partitioning into Expanders

Let G=(V,E) be an undirected graph, lambda_k be the k-th smallest eigenv...

Please sign up or login with your details

Forgot password? Click here to reset