Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Combinatorial optimization with physics-inspired graph neural networks

Nature Machine Intelligence volume 4, pages 367–377 (2022)Cite this article

Subjects

Matters Arising to this article was published on 30 December 2022

Matters Arising to this article was published on 30 December 2022

A preprint version of the article is available at arXiv.

Abstract

Combinatorial optimization problems are pervasive across science and industry. Modern deep learning tools are poised to solve these problems at unprecedented scales, but a unifying framework that incorporates insights from statistical physics is still outstanding. Here we demonstrate how graph neural networks can be used to solve combinatorial optimization problems. Our approach is broadly applicable to canonical NP-hard problems in the form of quadratic unconstrained binary optimization problems, such as maximum cut, minimum vertex cover, maximum independent set, as well as Ising spin glasses and higher-order generalizations thereof in the form of polynomial unconstrained binary optimization problems. We apply a relaxation strategy to the problem Hamiltonian to generate a differentiable loss function with which we train the graph neural network and apply a simple projection to integer variables once the unsupervised training process has completed. We showcase our approach with numerical results for the canonical maximum cut and maximum independent set problems. We find that the graph neural network optimizer performs on par or outperforms existing solvers, with the ability to scale beyond the state of the art to problems with millions of variables.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Schematic of the GNN approach for combinatorial optimization presented in this work.
Fig. 2: Flow chart illustrating the end-to-end workflow for the proposed physics-inspired GNN optimizer.
Fig. 3: Example solution to MaxCut for a random 3-regular graph with n = 100 nodes.
Fig. 4: Numerical results for MaxCut.
Fig. 5: Numerical results for the MIS problem.

Similar content being viewed by others

Data availability

The data necessary to reproduce our numerical benchmark results are publicly available at https://web.stanford.edu/~yyye/yyye/Gset/. Random d-regular graphs have been generated using the open-source networkx library (https://networkx.org).

Code availability

An end-to-end open source demo version of the code implementing our approach has been made publicly available at https://github.com/amazon-research/co-with-gnns-example116.

References

  1. Glover, F., Kochenberger, G. & Du, Y. Quantum bridge analytics I: a tutorial on formulating and using QUBO models. 4OR 17, 335 (2019).

    Article  MATH  Google Scholar 

  2. Kochenberger, G. et al. The unconstrained binary quadratic programming problem: a survey. J. Comb. Optim. 28, 58–81 (2014).

    Article  MATH  Google Scholar 

  3. Anthony, M., Boros, E., Crama, Y. & Gruber, A. Quadratic reformulations of nonlinear binary optimization problems. Math. Program. 162, 115–144 (2017).

    Article  MATH  Google Scholar 

  4. Papadimitriou, C. H. & Steiglitz, K. Combinatorial Optimization: Algorithms and Complexity (Courier Corporation, 1998).

    MATH  Google Scholar 

  5. Korte, B. & Vygen, J. Combinatorial Optimization Vol. 2 (Springer, 2012).

  6. Johnson, M. W. et al. Quantum annealing with manufactured spins. Nature 473, 194–198 (2011).

    Article  Google Scholar 

  7. Bunyk, P. et al. Architectural considerations in the design of a superconducting quantum annealing processor. IEEE Trans. Appl. Supercond. 24, 1–10 (2014).

    Article  Google Scholar 

  8. Katzgraber, H. G. Viewing vanilla quantum annealing through spin glasses. Quantum Sci. Technol. 3, 030505 (2018).

    Article  Google Scholar 

  9. Hauke, P., Katzgraber, H. G., Lechner, W., Nishimori, H. & Oliver, W. Perspectives of quantum annealing: methods and implementations. Rep. Prog. Phys. 83, 054401 (2020).

    Article  Google Scholar 

  10. Kadowaki, T. & Nishimori, H. Quantum annealing in the transverse Ising model. Phys. Rev. E 58, 5355 (1998).

    Article  Google Scholar 

  11. Farhi, E. et al. A quantum adiabatic evolution algorithm applied to random instances of an NP-complete problem. Science 292, 472–475 (2001).

    Article  MATH  Google Scholar 

  12. Mandrà, S., Zhu, Z., Wang, W., Perdomo-Ortiz, A. & Katzgraber, H. G. Strengths and weaknesses of weak-strong cluster problems: a detailed overview of state-of-the-art classical heuristics versus quantum approaches. Phys. Rev. A 94, 022337 (2016).

    Article  Google Scholar 

  13. Mandrà, S. & Katzgraber, H. G. A deceptive step towards quantum speedup detection. Quantum Sci. Technol. 3, 04LT01 (2018).

    Article  Google Scholar 

  14. Barzegar, A., Pattison, C., Wang, W. & Katzgraber, H. G. Optimization of population annealing Monte Carlo for large-scale spin-glass simulations. Phys. Rev. E 98, 053308 (2018).

    Article  Google Scholar 

  15. Hibat-Allah, M. et al. Variational neural annealing. Nat. Mach. Intell. 3, 952–961 (2021).

    Article  Google Scholar 

  16. Wang, Z., Marandi, A., Wen, K., Byer, R. L. & Yamamoto, Y. Coherent Ising machine based on degenerate optical parametric oscillators. Phys. Rev. A 88, 063853 (2013).

    Article  Google Scholar 

  17. Hamerly, R. et al. Scaling advantages of all-to-all connectivity in physical annealers: the coherent Ising machine vs. D-wave 2000Q. Sci. Adv. 5, eaau0823 (2019).

    Article  Google Scholar 

  18. Di Ventra, M. & Traversa, F. L. Perspective: memcomputing: leveraging memory and physics to compute efficiently. J. Appl. Phys. 123, 180901 (2018).

    Article  Google Scholar 

  19. Traversa, F. L., Ramella, C., Bonani, F. & Di Ventra, M. Memcomputing NP-complete problems in polynomial time using polynomial resources and collective states. Sci. Adv. 1, e1500031 (2015).

  20. Matsubara, S. et al. in Complex, Intelligent and Software Intensive Systems (CISIS-2017) (eds Terzo, O. & Barolli, L.) 432–438 (Springer, 2017).

  21. Tsukamoto, S., Takatsu, M., Matsubara, S. & Tamura, H. An accelerator architecture for combinatorial optimization problems. FUJITSU Sci. Tech. J. 53, 8–13 (2017).

    Google Scholar 

  22. Aramon, M., Rosenberg, G., Miyazawa, T., Tamura, H. & Katzgraber, H. G. Physics-inspired optimization for constraint-satisfaction problems using a digital annealer. Front. Phys. 7, 48 (2019).

    Article  Google Scholar 

  23. Gori, M., Monfardini, G. & Scarselli, F. A new model for learning in graph domains. In Proc. 2005 IEEE International Joint Conference on Neural Networks Vol. 2 729–734 (IEEE, 2005).

  24. Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M. & Monfardini, G. The graph neural network model. IEEE Trans. Neural Netw. 20, 61–80 (2008).

    Article  Google Scholar 

  25. Micheli, A. Neural network for graphs: a contextual constructive approach. IEEE Trans. Neural Netw. 20, 498–511 (2009).

    Article  Google Scholar 

  26. Duvenaud, D. K. et al. Convolutional networks on graphs for learning molecular fingerprints. Adv. Neural Inf. Process. Syst. 28, 2224–2232 (2015).

    Google Scholar 

  27. Hamilton, W. L., Ying, R. & Leskovec, J. Representation learning on graphs: methods and applications. Preprint at https://arxiv.org/abs/1709.05584 (2017).

  28. Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? Preprint at https://arxiv.org/abs/1810.00826 (2018).

  29. Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. Preprint at https://arxiv.org/abs/1609.02907 (2016).

  30. Wu, Z. et al. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. 32, 4–24 (2021).

    Article  Google Scholar 

  31. Perozzi, B., Al-Rfou, R. & Skiena, S. Deepwalk: online learning of social representations. In Proc. 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 701–710 (ACM, 2014).

  32. Sun, Z., Deng, Z. H., Nie, J. Y. & Tang, J. Rotate: knowledge graph embedding by relational rotation in complex space. Preprint at https://arxiv.org/abs/1902.10197 (2019).

  33. Ying, R. et al. Graph convolutional neural networks for web-scale recommender systems. In Proc. 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’18) 974–983 (ACM, 2018).

  34. Strokach, A., Becerra, D., Corbi-Verge, C., Perez-Riba, A. & Kim, P. M. Fast and flexible protein design using deep graph neural networks. Cell Syst. 11, 402–411 (2020).

    Article  Google Scholar 

  35. Gaudelet, T. et al. Utilising graph machine learning within drug discovery and development. Preprint at https://arxiv.org/abs/2012.05716 (2020).

  36. Pal, A. et al. Pinnersage: multi-modal user embedding framework for recommendations at Pinterest. In Proc. 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2311–2320 (ACM, 2020).

  37. Rossi, E. et al. Temporal graph networks for deep learning on dynamic graphs. Preprint at https://arxiv.org/abs/2006.10637 (2020).

  38. Monti, F., Frasca, F., Eynard, D., Mannion, D. & Bronstein, M. Fake news detection on social media using geometric deep learning. Preprint at https://arxiv.org/abs/1902.06673 (2019).

  39. Choma, N. et al. Graph neural networks for icecube signal classification. In 17th IEEE International Conference on Machine Learning and Applications (ICMLA) 386–391 (IEEE, 2018).

  40. Shlomi, J., Battaglia, P. & Vlimant, J.-R. Graph neural networks in particle physics. Mach. Learn. Sci. Technol. 2, 021001 (2020).

    Article  Google Scholar 

  41. Li, Y., Tarlow, D., Brockschmidt, M. & Zemel, R. Gated graph sequence neural networks. Preprint at https://arxiv.org/abs/1511.05493 (2015).

  42. Veličković, P. et al. Graph attention networks. Preprint at https://arxiv.org/abs/1710.10903 (2017).

  43. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. In International Conference on Machine Learning 1263–1272 (PMLR, 2017).

  44. Xu, K. et al. Representation learning on graphs with jumping knowledge networks. In International Conference on Machine Learning 5453–5462 (PMLR, 2018).

  45. Zheng, D. et al. DistDGL: distributed graph neural network training for billion-scale graphs. In IEEE/ACM 10th Workshop on Irregular Applications: Architectures and Algorithms (IA3) 36–44 (IEEE, 2020).

  46. Kotary, J., Fioretto, F., Van Hentenryck, P. & Wilder, B. End-to-end constrained optimization learning: a survey. Preprint at https://arxiv.org/abs/2103.16378 (2021).

  47. Cappart, Q. et al. Combinatorial optimization and reasoning with graph neural networks. Preprint at https://arxiv.org/abs/2102.09544 (2021).

  48. Mills, K., Ronagh, P. & Tamblyn, I. Finding the ground state of spin Hamiltonians with reinforcement learning. Nat. Mach. Intell. 2, 509–517 (2020).

    Article  Google Scholar 

  49. Vinyals, O., Fortunato, M. & Jaitly, N. Pointer networks. Adv. Neural Inf. Process. Syst. 28, 2692–2700 (2015).

    Google Scholar 

  50. Nowak, A., Villar, S., Bandeira, A. S. & Bruna, J. Revised note on learning algorithms for quadratic assignment with graph neural networks. Preprint at https://arxiv.org/abs/1706.07450 (2017).

  51. Bai, Y. et al. SimGNN: a neural network approach to fast graph similarity computation. Preprint at https://arxiv.org/abs/1808.05689 (2018).

  52. Lemos, H., Prates, M., Avelar, P. & Lamb, L. Graph colouring meets deep learning: effective graph neural network models for combinatorial problems. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) 879–885 (IEEE, 2019).

  53. Li, Z., Chen, Q. & Koltun, V. Combinatorial optimization with graph convolutional networks and guided tree search. In Proc. NeurIPS 536–545 (2018).

  54. Joshi, C. K., Laurent, T. & Bresson, X. An efficient graph convolutional network technique for the travelling salesman problem. Preprint at https://arxiv.org/abs/1906.01227 (2019).

  55. Karalias, N. & Loukas, A. Erdos goes neural: an unsupervised learning framework for combinatorial optimization on graphs. Preprint at https://arxiv.org/abs/2006.10643 (2020).

  56. Yehuda, G., Gabel, M. & Schuster, A. It’s not what machines can learn, it’s what we cannot teach. Preprint at https://arxiv.org/abs/2002.09398 (2020).

  57. Bello, I., Pham, H., Le, Q. V., Norouzi, M. & Bengio, S. Neural combinatorial optimization with reinforcement learning. Preprint at https://arxiv.org/abs/1611.09940 (2017).

  58. Kool, W., van Hoof, H. & Welling, M. Attention, learn to solve routing problems! Preprint at https://arxiv.org/abs/1803.08475 (2019).

  59. Ma, Q., Ge, S., He, D., Thaker, D. & Drori, I. Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning. Preprint at https://arxiv.org/abs/1911.04936 (2019).

  60. Dai, H., Khalil, E. B., Zhang, Y., Dilkina, B. & Song, L. Learning combinatorial optimization algorithms over graphs. In Annual Conference on Neural Information Processing Systems (NIPS) 6351–6361 (2017).

  61. Toenshoff, J., Ritzert, M., Wolf, H. & Grohe, M. RUN-CSP: unsupervised learning of message passing networks for binary constraint satisfaction problems. Preprint at https://arxiv.org/abs/1909.08387 (2019).

  62. Yao, W., Bandeira, A. S. & Villar, S. Experimental performance of graph neural networks on random instances of max-cut. In Wavelets and Sparsity XVIII Vol. 11138 111380S (International Society for Optics and Photonics, 2019).

  63. Ising, E. Beitrag zur Theorie des Ferromagnetismus. Z. Phys. 31, 253–258 (1925).

    Article  MATH  Google Scholar 

  64. Matsubara, S., et al. Ising-model optimizer with parallel-trial bit-sieve engine. In Conference on Complex, Intelligent, and Software Intensive Systems 432–438 (Springer, 2017).

  65. Hamerly, R. et al. Experimental investigation of performance differences between coherent Ising machines and a quantum annealer. Sci. Adv. 5, eaau0823 (2019).

    Article  Google Scholar 

  66. Lucas, A. Ising formulations of many NP problems. Front. Phys. 2, 5 (2014).

    Article  Google Scholar 

  67. Alon, U. & Yahav, E. On the bottleneck of graph neural networks and its practical implications. Preprint at https://arxiv.org/abs/2006.05205 (2020).

  68. Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch Geometric. Preprint at https://arxiv.org/abs/1903.02428 (2019).

  69. Wang, M. et al. Deep Graph Library: a graph-centric, highly-performant package for graph neural networks. Preprint at https://arxiv.org/abs/1909.01315 (2019).

  70. Alidaee, B., Kochenberger, G. A. & Ahmadian, A. 0-1 Quadratic programming approach for optimum solutions of two scheduling problems. Int. J. Syst. Sci. 25, 401–408 (1994).

    Article  MATH  Google Scholar 

  71. Neven, H., Rose, G. & Macready, W. G. Image recognition with an adiabatic quantum computer I. Mapping to quadratic unconstrained binary optimization. Preprint at https://arxiv.org/abs/0804.4457 (2008).

  72. Deza, M. & Laurent, M. Applications of cut polyhedra. J. Comput. Appl. Math. 55, 191–216 (1994).

    Article  MATH  Google Scholar 

  73. Farhi, E., Goldstone, J. & Gutmann, S. A. A quantum approximate optimization algorithm. Preprint at https://arxiv.org/abs/1411.4028 (2014).

  74. Zhou, L., Wang, S.-T., Choi, S., Pichler, H. & Lukin, M. D. Quantum approximate optimization algorithm: performance, mechanism and implementation on near-term devices. Phys. Rev. X 10, 021067 (2020).

    Google Scholar 

  75. Guerreschi, G. G. & Y., A. QAOA for Max-Cut requires hundreds of qubits for quantum speed-up. Nat. Sci. Rep. 9, 6903 (2019).

    Google Scholar 

  76. Crooks, G. E. Performance of the quantum approximate optimization algorithm on the maximum cut problem. Preprint at https://arxiv.org/abs/1811.08419 (2018).

  77. Lotshaw, P. C. et al. Empirical performance bounds for quantum approximate optimization. Quantum Inf. Process. 20, 403 (2021).

    Article  MATH  Google Scholar 

  78. Patti, T. L., Kossaifi, J., Anandkumar, A. & Yelin, S. F. Variational Quantum Optimization with Multi-Basis Encodings. Preprint at https://arxiv.org/abs/2106.13304 (2021).

  79. Zhao, T., Carleo, G., Stokes, J. & Veerapaneni, S. Natural evolution strategies and variational Monte Carlo. Mach. Learn. Sci. Technol. 2, 02LT01 (2020).

    Article  Google Scholar 

  80. Goemans, M. X. & Williamson, D. P. Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming. J. ACM 42, 1115–1145 (1995).

    Article  MATH  Google Scholar 

  81. Halperin, E., Livnat, D. & Zwick, U. MAX CUT in cubic graphs. J. Algorithms 53, 169–185 (2004).

    Article  MATH  Google Scholar 

  82. Dembo, A., Montanari, A. & Sen, S. Extremal cuts of sparse random graphs. Ann. Probab. 45, 1190–1217 (2017).

    Article  MATH  Google Scholar 

  83. Sherrington, D. & Kirkpatrick, S. Solvable model of a spin glass. Phys. Rev. Lett. 35, 1792–1795 (1975).

    Article  Google Scholar 

  84. Binder, K. & Young, A. P. Spin glasses: experimental facts, theoretical concepts and open questions. Rev. Mod. Phys. 58, 801–976 (1986).

    Article  Google Scholar 

  85. Alizadeh, F. Interior point methods in semidefinite programming with applications to combinatorial optimization. SIAM J. Optimization 5, 13 (1995).

    Article  MATH  Google Scholar 

  86. Haribara, Y. & Utsunomiya, S. in Principles and Methods of Quantum Information Technologies. Lecture Notes in Physics Vol. 911 (eds Semba, K. & Yamamoto, Y.) 251–262 (Springer, 2016).

  87. Ye, Y. The Gset Dataset (Stanford, 2003); https://web.stanford.edu/~yyye/yyye/Gset/

  88. Kochenberger, G. A., Hao, J.-K., Lu, Z., Wang, H. & Glover, F. Solving large scale Max Cut problems via tabu search. J. Heuristics 19, 565–571 (2013).

    Article  Google Scholar 

  89. Benlic, U. & Hao, J.-K. Breakout local search for the Max-Cut problem. Eng. Appl. Artif. Intell. 26, 1162–1173 (2013).

    Article  MATH  Google Scholar 

  90. Choi, C. & Ye, Y. Solving Sparse Semidefinite Programs Using the Dual Scaling Algorithm with an Iterative Solver Working Paper (Department of Management Sciences, Univ. Iowa, 2000).

  91. Hale, W. K. Frequency assignment: theory and applications. Proc. IEEE 68, 1497–1514 (1980).

    Article  Google Scholar 

  92. Boginski, V., Butenko, S. & Pardalos, P. M. Statistical analysis of financial networks. Comput. Stat. Data Anal. 48, 431–443 (2005).

    Article  MATH  Google Scholar 

  93. Yu, H., Wilczek, F. & Wu, B. Quantum algorithm for approximating maximum independent sets. Chin. Phys. Lett. 38, 030304 (2021).

    Article  Google Scholar 

  94. Pichler, H., Wang, S.-T., Zhou, L., Choi, S. & Lukin, M. D. Quantum optimization for maximum independent set using Rydberg atom arrays. Preprint at https://arxiv.org/abs/1808.10816 (2018).

  95. Djidjev, H. N., Chapuis, G., Hahn, G. & Rizk, G. Efficient combinatorial optimization using quantum annealing. Preprint at https://arxiv.org/abs/1801.08653 (2018).

  96. Boppana, R. & Halldórsson, M. M. Approximating maximum independent sets by excluding subgraphs. BIT Numer. Math. 32, 180–196 (1992).

    Article  MATH  Google Scholar 

  97. Duckworth, W. & Zito, M. Large independent sets in random regular graphs. Theor. Comput. Sci. 410, 5236–5243 (2009).

    Article  MATH  Google Scholar 

  98. McKay, B. D. Independent sets in regular graphs of high girth. Ars Combinatoria 23A, 179 (1987).

    MATH  Google Scholar 

  99. Grötschel, M., Jünger, M. & Reinelt, G. An application of combinatorial optimization to statistical physics and circuit layout design. Oper. Res. 36, 493–513 (1988).

    Article  MATH  Google Scholar 

  100. Laughhunn, D. J. Quadratic binary programming with application to capital-budgeting problems. Oper. Res. 18, 454–461 (1970).

    Article  MATH  Google Scholar 

  101. Krarup, J. & Pruzan, A. Computer aided layout design. Math. Program. Study 9, 75–94 (1978).

    Article  MATH  Google Scholar 

  102. Gallo, G., Hammer, P. & Simeone, B. Quadratic knapsack problems. Math. Program. 12, 132–149 (1980).

    Article  MATH  Google Scholar 

  103. Witsgall, C. Mathematical Methods of Site Selection for Electronic System (EMS) NBS Internal Report (NBS, 1975).

  104. Chardaire, P. & Sutter, A. A decomposition method for quadratic zero-one programming. Manag. Sci. 41, 704–712 (1994).

    Article  MATH  Google Scholar 

  105. Phillips, A. & Rosen, J. B. A quadratic assignment formulation of the molecular conformation problem. J. Glob. Optim. 4, 229–241 (1994).

    Article  MATH  Google Scholar 

  106. Iasemidis, L. D. et al. Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity. Optim. Methods Software 18, 81–104 (2003).

    Article  MATH  Google Scholar 

  107. Kalra, A., Qureshi, F. & Tisi, M. Portfolio asset identification using graph algorithms on a quantum annealer. SSRN https://ssrn.com/abstract=3333537 (2018).

  108. Markowitz, H. Portfolio selection. J. Finance 7, 77–91 (1952).

    Google Scholar 

  109. Kolen, A. Interval scheduling: a survey. Naval Res. Logist. 54, 530–543 (2007).

    Article  MATH  Google Scholar 

  110. Bar-Noy, A., Bar-Yehuda, R., Freund, A., Naor, J. & Schieber, B. A unified approach to approximating resource allocation and scheduling. J. ACM 48, 1069–1090 (2001).

    Article  MATH  Google Scholar 

  111. Speziali, S. et al. Solving sensor placement problems in real water distribution networks using adiabatic quantum computation. In 2021 IEEE International Conference on Quantum Computing and Engineering (QCE) 463–464 (IEEE, 2021).

  112. McMahon, P. L. et al. A fully programmable 100-spin coherent Ising machine with all-to-all connections. Science 354, 614–617 (2016).

    Article  Google Scholar 

  113. Bansal, N. & Khot, S. Inapproximability of hypergraph vertex cover and applications to scheduling problems. In Proc. Automata, Languages and Programming (ICALP 2010) Lecture Notes in Computer Science Vol. 6198 (eds Abramsky, S. et al.) 250–261 (Springer, 2010).

  114. Hernandez, M., Zaribafiyan, A., Aramon, M. & Naghibi, M. A novel graph-based approach for determining molecular similarity. Preprint at https://arxiv.org/abs/1601.06693 (2016).

  115. Terry, J. P., Akrobotu, P. D., Negre, C. F. & Mniszewski, S. M. Quantum isomer search. PLoS ONE 15, e0226787 (2020).

    Article  Google Scholar 

  116. Combinatorial optimization with graph neural networks. GitHub https://github.com/amazon-research/co-with-gnns-example (2022).

Download references

Acknowledgements

We thank F. Brandao, G. Karypis, M. Kastoryano, E. Kessler, T. Mullenbach, N. Pancotti, M. Resende, S. Roy, G. Salton, S. Severini, A. Urweisse and J. Zhu for fruitful discussions.

Author information

Authors and Affiliations

  1. Amazon Quantum Solutions Lab, Seattle, WA, USA

    Martin J. A. Schuetz & Helmut G. Katzgraber

  2. AWS Intelligent and Advanced Compute Technologies, Professional Services, Seattle, WA, USA

    Martin J. A. Schuetz, J. Kyle Brubaker & Helmut G. Katzgraber

  3. AWS Center for Quantum Computing, Pasadena, CA, USA

    Martin J. A. Schuetz & Helmut G. Katzgraber

Authors
  1. Martin J. A. Schuetz
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. Kyle Brubaker
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Helmut G. Katzgraber
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the ideation and design of the research. M.J.A.S. and J.K.B. developed and ran the computational experiments and also wrote the initial draft of the the manuscript. H.G.K. supervised this work and revised the manuscript.

Corresponding authors

Correspondence to Martin J. A. Schuetz, J. Kyle Brubaker or Helmut G. Katzgraber.

Ethics declarations

Competing interests

M.J.A.S., J.K.B. and H.G.K. are listed as inventors on a US provisional patent application (no. 7924-38500) on combinatorial optimization with graph neural networks.

Peer review

Peer review information

Nature Machine Intelligence thanks Thomas Vandal and Estelle Inack for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary listings 1 and 2 and Table 1.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Schuetz, M.J.A., Brubaker, J.K. & Katzgraber, H.G. Combinatorial optimization with physics-inspired graph neural networks. Nat Mach Intell 4, 367–377 (2022). https://doi.org/10.1038/s42256-022-00468-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-022-00468-6

This article is cited by

Search

Advanced search

Quick links

Nature Briefing AI and Robotics

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing: AI and Robotics