Share Email Print

Proceedings Paper

Discrete optimizations using graph convolutional networks
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 9 September 2019
PDF: 11 pages
Proc. SPIE 11138, Wavelets and Sparsity XVIII, 1113806 (9 September 2019); doi: 10.1117/12.2529432
Show Author Affiliations
Radu Balan, Univ. of Maryland, College Park (United States)
Naveed Haghani, Univ. of Maryland, College Park (United States)

Published in SPIE Proceedings Vol. 11138:
Wavelets and Sparsity XVIII
Dimitri Van De Ville; Manos Papadakis; Yue M. Lu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?