REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS

Alex Nowak, Soledad Villar, Afonso Bandeira, Joan Bruna Estrach

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Inverse problems correspond to a certain type of optimization problems formulated over appropriate input distributions. Recently, there has been a growing interest in understanding the computational hardness of these optimization problems, not only in the worst case, but in an average-complexity sense under this same input distribution.In this revised note, we are interested in studying another aspect of hardness, related to the ability to learn how to solve a problem by simply observing a collection of previously solved instances. These 'planted solutions' are used to supervise the training of an appropriate predictive model that parametrizes a broad class of algorithms, with the hope that the resulting model will provide good accuracy-complexity tradeoffs in the average sense.We illustrate this setup on the Quadratic Assignment Problem, a fundamental problem in Network Science. We observe that data-driven models based on Graph Neural Networks offer intriguingly good performance, even in regimes where standard relaxation based techniques appear to suffer.

Original languageEnglish (US)
Title of host publication2018 IEEE Data Science Workshop, DSW 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages229-233
Number of pages5
ISBN (Print)9781538644102
DOIs
StatePublished - Aug 17 2018
Event2018 IEEE Data Science Workshop, DSW 2018 - Lausanne, Switzerland
Duration: Jun 4 2018Jun 6 2018

Other

Other2018 IEEE Data Science Workshop, DSW 2018
CountrySwitzerland
CityLausanne
Period6/4/186/6/18

Fingerprint

Hardness
Average Complexity
Optimization Problem
Quadratic Assignment Problem
hardness
Predictive Model
Data-driven
Inverse Problem
Trade-offs
Neural Networks
Model-based
inverse problem
Inverse problems
Graph in graph theory
Neural networks
Model
distribution
Class
Standards
Training

ASJC Scopus subject areas

  • Artificial Intelligence
  • Safety, Risk, Reliability and Quality
  • Water Science and Technology
  • Control and Optimization

Cite this

Nowak, A., Villar, S., Bandeira, A., & Bruna Estrach, J. (2018). REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS. In 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings (pp. 229-233). [8439919] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DSW.2018.8439919

REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS. / Nowak, Alex; Villar, Soledad; Bandeira, Afonso; Bruna Estrach, Joan.

2018 IEEE Data Science Workshop, DSW 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 229-233 8439919.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nowak, A, Villar, S, Bandeira, A & Bruna Estrach, J 2018, REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS. in 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings., 8439919, Institute of Electrical and Electronics Engineers Inc., pp. 229-233, 2018 IEEE Data Science Workshop, DSW 2018, Lausanne, Switzerland, 6/4/18. https://doi.org/10.1109/DSW.2018.8439919
Nowak A, Villar S, Bandeira A, Bruna Estrach J. REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS. In 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 229-233. 8439919 https://doi.org/10.1109/DSW.2018.8439919
Nowak, Alex ; Villar, Soledad ; Bandeira, Afonso ; Bruna Estrach, Joan. / REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS. 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 229-233
@inproceedings{6ba5b9dc4a2640269b5769e7018f0c0f,
title = "REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS",
abstract = "Inverse problems correspond to a certain type of optimization problems formulated over appropriate input distributions. Recently, there has been a growing interest in understanding the computational hardness of these optimization problems, not only in the worst case, but in an average-complexity sense under this same input distribution.In this revised note, we are interested in studying another aspect of hardness, related to the ability to learn how to solve a problem by simply observing a collection of previously solved instances. These 'planted solutions' are used to supervise the training of an appropriate predictive model that parametrizes a broad class of algorithms, with the hope that the resulting model will provide good accuracy-complexity tradeoffs in the average sense.We illustrate this setup on the Quadratic Assignment Problem, a fundamental problem in Network Science. We observe that data-driven models based on Graph Neural Networks offer intriguingly good performance, even in regimes where standard relaxation based techniques appear to suffer.",
author = "Alex Nowak and Soledad Villar and Afonso Bandeira and {Bruna Estrach}, Joan",
year = "2018",
month = "8",
day = "17",
doi = "10.1109/DSW.2018.8439919",
language = "English (US)",
isbn = "9781538644102",
pages = "229--233",
booktitle = "2018 IEEE Data Science Workshop, DSW 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - REVISED NOTE on LEARNING QUADRATIC ASSIGNMENT with GRAPH NEURAL NETWORKS

AU - Nowak, Alex

AU - Villar, Soledad

AU - Bandeira, Afonso

AU - Bruna Estrach, Joan

PY - 2018/8/17

Y1 - 2018/8/17

N2 - Inverse problems correspond to a certain type of optimization problems formulated over appropriate input distributions. Recently, there has been a growing interest in understanding the computational hardness of these optimization problems, not only in the worst case, but in an average-complexity sense under this same input distribution.In this revised note, we are interested in studying another aspect of hardness, related to the ability to learn how to solve a problem by simply observing a collection of previously solved instances. These 'planted solutions' are used to supervise the training of an appropriate predictive model that parametrizes a broad class of algorithms, with the hope that the resulting model will provide good accuracy-complexity tradeoffs in the average sense.We illustrate this setup on the Quadratic Assignment Problem, a fundamental problem in Network Science. We observe that data-driven models based on Graph Neural Networks offer intriguingly good performance, even in regimes where standard relaxation based techniques appear to suffer.

AB - Inverse problems correspond to a certain type of optimization problems formulated over appropriate input distributions. Recently, there has been a growing interest in understanding the computational hardness of these optimization problems, not only in the worst case, but in an average-complexity sense under this same input distribution.In this revised note, we are interested in studying another aspect of hardness, related to the ability to learn how to solve a problem by simply observing a collection of previously solved instances. These 'planted solutions' are used to supervise the training of an appropriate predictive model that parametrizes a broad class of algorithms, with the hope that the resulting model will provide good accuracy-complexity tradeoffs in the average sense.We illustrate this setup on the Quadratic Assignment Problem, a fundamental problem in Network Science. We observe that data-driven models based on Graph Neural Networks offer intriguingly good performance, even in regimes where standard relaxation based techniques appear to suffer.

UR - http://www.scopus.com/inward/record.url?scp=85053131950&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053131950&partnerID=8YFLogxK

U2 - 10.1109/DSW.2018.8439919

DO - 10.1109/DSW.2018.8439919

M3 - Conference contribution

SN - 9781538644102

SP - 229

EP - 233

BT - 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -