Combinatorial optimization and reasoning with graph neural networks release_eweej3mq2bbohaifazeghswcpi

by Quentin Cappart, Didier Chételat, Elias Khalil, Andrea Lodi, Christopher Morris, Petar Veličković

Released as a article .

2021  

Abstract

Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolation, ignoring the fact that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning, especially graph neural networks (GNNs), as a key building block for combinatorial tasks, either directly as solvers or by enhancing exact solvers. The inductive bias of GNNs effectively encodes combinatorial and relational input due to their invariance to permutations and awareness of input sparsity. This paper presents a conceptual review of recent key advancements in this emerging field, aiming at researchers in both optimization and machine learning.
In text/plain format

Archived Files and Locations

application/pdf  1.1 MB
file_mdt2sjkkbnfxdi5epmudtlbg3e
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-04-27
Version   v2
Language   en ?
arXiv  2102.09544v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: b1433f6b-fcdb-4598-8af5-98683ef511fe
API URL: JSON