Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Learning and Spectral Embedding for Graph Partitioning

About

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.

Alice Gatti, Zhixiong Hu, Tess Smidt, Esmond G. Ng, Pieter Ghysels• 2021

Related benchmarks

TaskDatasetResultRank
Sparse Matrix ReorderingSuiteSparse Matrix Collection 150 1.0 (test)
MSP Mean Time (s)81
7
Sparse Matrix ReorderingSuiteSparse 150 (test)
Mean MSP Score55.66
7
Showing 2 of 2 rows

Other info

Follow for update