Back to Search Start Over

Deep Learning and Spectral Embedding for Graph Partitioning

Authors :
Gatti, Alice
Hu, Zhixiong
Smidt, Tess
Ng, Esmond G.
Ghysels, Pieter
Publication Year :
2021

Abstract

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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2110.08614
Document Type :
Working Paper