GL-Coarsener: A Graph representation learning framework to construct coarse grid hierarchy for AMG solvers

TL;DR

This paper introduces GL-Coarsener, a novel graph representation learning framework that constructs coarse grids for algebraic multigrid solvers, leveraging machine learning to improve efficiency and scalability in solving large linear systems.

Contribution

It presents a new aggregation-based coarsening method using graph representation learning, integrating machine learning into AMG to enhance grid construction.

Findings

Comparable efficiency with existing aggregation methods

Effective parallel computation capabilities

Demonstrated potential of graph learning in AMG design

Abstract

In many numerical schemes, the computational complexity scales non-linearly with the problem size. Solving a linear system of equations using direct methods or most iterative methods is a typical example. Algebraic multi-grid (AMG) methods are numerical methods used to solve large linear systems of equations efficiently. One of the main differences between AMG methods is how the coarser grid is constructed from a given fine grid. There are two main classes of AMG methods; graph and aggregation based coarsening methods. Here we propose an aggregation-based coarsening framework leveraging graph representation learning and clustering algorithms. Our method introduces the power of machine learning into the AMG research field and opens a new perspective for future researches. The proposed method uses graph representation learning techniques to learn latent features of the graph obtained from the underlying matrix of coefficients. Using these extracted features, we generated a coarser grid from the fine grid. The proposed method is highly capable of parallel computations. Our experiments show that the proposed method's efficiency in solving large systems is closely comparable with other aggregation-based methods, demonstrating the high capability of graph representation learning in designing multi-grid solvers.