Cracking nuts with a sledgehammer: when modern graph neural networks do worse than classical greedy algorithms

by   Maria Chiara Angelini, et al.

The recent work “Combinatorial Optimization with Physics-Inspired Graph Neural Networks” [Nat Mach Intell 4 (2022) 367] introduces a physics-inspired unsupervised Graph Neural Network (GNN) to solve combinatorial optimization problems on sparse graphs. To test the performances of these GNNs, the authors of the work show numerical results for two fundamental problems: maximum cut and maximum independent set (MIS). They conclude that "the graph neural network optimizer performs on par or outperforms existing solvers, with the ability to scale beyond the state of the art to problems with millions of variables." In this comment, we show that a simple greedy algorithm, running in almost linear time, can find solutions for the MIS problem of much better quality than the GNN. The greedy algorithm is faster by a factor of 10^4 with respect to the GNN for problems with a million variables. We do not see any good reason for solving the MIS with these GNN, as well as for using a sledgehammer to crack nuts. In general, many claims of superiority of neural networks in solving combinatorial problems are at risk of being not solid enough, since we lack standard benchmarks based on really hard problems. We propose one of such hard benchmarks, and we hope to see future neural network optimizers tested on these problems before any claim of superiority is made.


page 1

page 2

page 3

page 4


Combinatorial Optimization with Physics-Inspired Graph Neural Networks

We demonstrate how graph neural networks can be used to solve combinator...

Barriers for the performance of graph neural networks (GNN) in discrete random structures. A comment on <cit.>,<cit.>,<cit.>

Recently graph neural network (GNN) based algorithms were proposed to so...

On Representing Linear Programs by Graph Neural Networks

Learning to optimize is a rapidly growing area that aims to solve optimi...

Flex-Net: A Graph Neural Network Approach to Resource Management in Flexible Duplex Networks

Flexible duplex networks allow users to dynamically employ uplink and do...

Neural combinatorial optimization beyond the TSP: Existing architectures under-represent graph structure

Recent years have witnessed the promise that reinforcement learning, cou...

Please sign up or login with your details

Forgot password? Click here to reset