On Representing Mixed-Integer Linear Programs by Graph Neural Networks

10/19/2022
by   Ziang Chen, et al.
0

While Mixed-integer linear programming (MILP) is NP-hard in general, practical MILP has received roughly 100–fold speedup in the past twenty years. Still, many classes of MILPs quickly become unsolvable as their sizes increase, motivating researchers to seek new acceleration techniques for MILPs. With deep learning, they have obtained strong empirical results, and many results were obtained by applying graph neural networks (GNNs) to making decisions in various stages of MILP solution processes. This work discovers a fundamental limitation: there exist feasible and infeasible MILPs that all GNNs will, however, treat equally, indicating GNN's lacking power to express general MILPs. Then, we show that, by restricting the MILPs to unfoldable ones or by adding random features, there exist GNNs that can reliably predict MILP feasibility, optimal objective values, and optimal solutions up to prescribed precision. We conducted small-scale numerical experiments to validate our theoretical findings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2021

Can Graph Neural Networks Learn to Solve MaxSAT Problem?

With the rapid development of deep learning techniques, various recent w...
research
09/25/2022

On Representing Linear Programs by Graph Neural Networks

Learning to optimize is a rapidly growing area that aims to solve optimi...
research
10/11/2020

A Practical Guide to Graph Neural Networks

Graph neural networks (GNNs) have recently grown in popularity in the fi...
research
09/24/2020

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

We study how neural networks trained by gradient descent extrapolate, i....
research
06/25/2020

Incremental Training of Graph Neural Networks on Temporal Graphs under Distribution Shift

Current graph neural networks (GNNs) are promising, especially when the ...
research
02/18/2021

Smart Feasibility Pump: Reinforcement Learning for (Mixed) Integer Programming

In this work, we propose a deep reinforcement learning (DRL) model for f...
research
06/30/2022

Lookback for Learning to Branch

The expressive and computationally inexpensive bipartite Graph Neural Ne...

Please sign up or login with your details

Forgot password? Click here to reset