Discrete optimizations using graph convolutional networks

Radu Balan; Naveed Haghani

doi:10.1117/12.2529432

9 September 2019 Discrete optimizations using graph convolutional networks

Radu Balan, Naveed Haghani

Proceedings Volume 11138, Wavelets and Sparsity XVIII; 1113806 (2019) https://doi.org/10.1117/12.2529432
Event: SPIE Optical Engineering + Applications, 2019, San Diego, California, United States

Abstract

In this paper we discuss the use of graph deep learning in solving quadratic assignment problems (QAP). The quadratic assignment problem is an NP hard optimization problem. We shall analyze an approach using Graph Convolutional Networks (GCN). We prove that a specially designed GCN produces the optimal solution for a broad class of assignment problems. By appropriate training, the class of problems correctly solved is thus enlarged. Numerical examples compare this method with other simpler methods.

Citation Download Citation

Radu Balan and Naveed Haghani "Discrete optimizations using graph convolutional networks", Proc. SPIE 11138, Wavelets and Sparsity XVIII, 1113806 (9 September 2019); https://doi.org/10.1117/12.2529432

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available