IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v8y2020i2p298-d323915.html
   My bibliography  Save this article

A Deep Learning Algorithm for the Max-Cut Problem Based on Pointer Network Structure with Supervised Learning and Reinforcement Learning Strategies

Author

Listed:
  • Shenshen Gu

    (School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
    Current address: 99 Shangda Road, Shanghai 200444, China.)

  • Yue Yang

    (School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China)

Abstract

The Max-cut problem is a well-known combinatorial optimization problem, which has many real-world applications. However, the problem has been proven to be non-deterministic polynomial-hard (NP-hard), which means that exact solution algorithms are not suitable for large-scale situations, as it is too time-consuming to obtain a solution. Therefore, designing heuristic algorithms is a promising but challenging direction to effectively solve large-scale Max-cut problems. For this reason, we propose a unique method which combines a pointer network and two deep learning strategies (supervised learning and reinforcement learning) in this paper, in order to address this challenge. A pointer network is a sequence-to-sequence deep neural network, which can extract data features in a purely data-driven way to discover the hidden laws behind data. Combining the characteristics of the Max-cut problem, we designed the input and output mechanisms of the pointer network model, and we used supervised learning and reinforcement learning to train the model to evaluate the model performance. Through experiments, we illustrated that our model can be well applied to solve large-scale Max-cut problems. Our experimental results also revealed that the new method will further encourage broader exploration of deep neural network for large-scale combinatorial optimization problems.

Suggested Citation

  • Shenshen Gu & Yue Yang, 2020. "A Deep Learning Algorithm for the Max-Cut Problem Based on Pointer Network Structure with Supervised Learning and Reinforcement Learning Strategies," Mathematics, MDPI, vol. 8(2), pages 1-20, February.
  • Handle: RePEc:gam:jmathe:v:8:y:2020:i:2:p:298-:d:323915
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/8/2/298/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/8/2/298/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jerker. Denrell & Christina. Fang & Daniel A. Levinthal, 2004. "From T-Mazes to Labyrinths: Learning from Model-Based Feedback," Management Science, INFORMS, vol. 50(10), pages 1366-1378, October.
    2. Francisco Barahona & Martin Grötschel & Michael Jünger & Gerhard Reinelt, 1988. "An Application of Combinatorial Optimization to Statistical Physics and Circuit Layout Design," Operations Research, INFORMS, vol. 36(3), pages 493-513, June.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Fuda Ma & Jin-Kao Hao, 2017. "A multiple search operator heuristic for the max-k-cut problem," Annals of Operations Research, Springer, vol. 248(1), pages 365-403, January.
    2. Dell'Amico, Mauro & Trubian, Marco, 1998. "Solution of large weighted equicut problems," European Journal of Operational Research, Elsevier, vol. 106(2-3), pages 500-521, April.
    3. Goldengorin, Boris, 2009. "Maximization of submodular functions: Theory and enumeration algorithms," European Journal of Operational Research, Elsevier, vol. 198(1), pages 102-112, October.
    4. Phanish Puranam, 2021. "Human–AI collaborative decision-making as an organization design problem," Journal of Organization Design, Springer;Organizational Design Community, vol. 10(2), pages 75-80, June.
    5. Xunzhao Yin & Yu Qian & Alptekin Vardar & Marcel Günther & Franz Müller & Nellie Laleni & Zijian Zhao & Zhouhang Jiang & Zhiguo Shi & Yiyu Shi & Xiao Gong & Cheng Zhuo & Thomas Kämpfe & Kai Ni, 2024. "Ferroelectric compute-in-memory annealer for combinatorial optimization problems," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
    6. Cheng Lu & Zhibin Deng, 2021. "A branch-and-bound algorithm for solving max-k-cut problem," Journal of Global Optimization, Springer, vol. 81(2), pages 367-389, October.
    7. Christina Fang & Daniel Levinthal, 2009. "Near-Term Liability of Exploitation: Exploration and Exploitation in Multistage Problems," Organization Science, INFORMS, vol. 20(3), pages 538-551, June.
    8. Gary Kochenberger & Jin-Kao Hao & Fred Glover & Mark Lewis & Zhipeng Lü & Haibo Wang & Yang Wang, 2014. "The unconstrained binary quadratic programming problem: a survey," Journal of Combinatorial Optimization, Springer, vol. 28(1), pages 58-81, July.
    9. Christina Fang & Jeho Lee & Melissa A. Schilling, 2010. "Balancing Exploration and Exploitation Through Structural Design: The Isolation of Subgroups and Organizational Learning," Organization Science, INFORMS, vol. 21(3), pages 625-642, June.
    10. Giovanni. Gavetti & Daniel A. Levinthal, 2004. "50th Anniversay Article: The Strategy Field from the Perspective of Management Science: Divergent Strands and Possible Integration," Management Science, INFORMS, vol. 50(10), pages 1309-1318, October.
    11. Jerker Denrell, 2004. "Comment: The Performance of Performance," Journal of Management & Governance, Springer;Accademia Italiana di Economia Aziendale (AIDEA), vol. 8(4), pages 345-349, October.
    12. repec:dgr:rugsom:99a17 is not listed on IDEAS
    13. Anindya Ghosh & Xavier Martin & Johannes M. Pennings & Filippo Carlo Wezel, 2014. "Ambition Is Nothing Without Focus: Compensating for Negative Transfer of Experience in R&D," Organization Science, INFORMS, vol. 25(2), pages 572-590, April.
    14. June-Young Kim & Ji-Yub (Jay) Kim & Anne S. Miner, 2009. "Organizational Learning from Extreme Performance Experience: The Impact of Success and Recovery Experience," Organization Science, INFORMS, vol. 20(6), pages 958-978, December.
    15. Oliver Baumann & Nicolaj Siggelkow, 2013. "Dealing with Complexity: Integrated vs. Chunky Search Processes," Organization Science, INFORMS, vol. 24(1), pages 116-132, February.
    16. Hart E. Posen & John S. Chen, 2013. "An Advantage of Newness: Vicarious Learning Despite Limited Absorptive Capacity," Organization Science, INFORMS, vol. 24(6), pages 1701-1716, December.
    17. Kent D. Miller & Shu-Jou Lin, 2010. "Different Truths in Different Worlds," Organization Science, INFORMS, vol. 21(1), pages 97-114, February.
    18. Fred Glover & Jin-Kao Hao, 2016. "f-Flip strategies for unconstrained binary quadratic programming," Annals of Operations Research, Springer, vol. 238(1), pages 651-657, March.
    19. Gili Rosenberg & Mohammad Vazifeh & Brad Woods & Eldad Haber, 2016. "Building an iterative heuristic solver for a quantum annealer," Computational Optimization and Applications, Springer, vol. 65(3), pages 845-869, December.
    20. Michael G. Jacobides & Sidney G. Winter, 2012. "Capabilities: Structure, Agency, and Evolution," Organization Science, INFORMS, vol. 23(5), pages 1365-1381, October.
    21. Goldengorin, Boris & Sierksma, Gerard & Tijssen, Gert A., 1998. "The data-correcting algorithm for supermodular functions, with applications to quadratic cost partition and simple plant location problems," Research Report 98A08, University of Groningen, Research Institute SOM (Systems, Organisations and Management).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:8:y:2020:i:2:p:298-:d:323915. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.