Document Open Access Logo

Using Reinforcement Learning to Optimize the Global and Local Crossing Number

Authors Timo Brand , Henry Förster , Stephen Kobourov , Daniel Kohrt, Robin Schukrafft, Markus Wallinger , Johannes Zink

PDF

File

Thumbnail PDF
PDF
LIPIcs.GD.2026.24.pdf
  • Filesize: 2.23 MB
  • 19 pages

Document Identifiers

Related Versions

Subject Classification

ACM Subject Classification
  • Theory of computation → Reinforcement learning
  • Theory of computation → Computational geometry
Keywords
  • Reinforcement Learning
  • Crossing Minimization
  • Local Crossing Number

Metrics

Abstract

Graph drawing concerns the algorithmic visualization of graphs. A good drawing of a graph is easy to read and facilitates solving tasks on the graph. Several properties have been identified to occur in good drawings of graphs. Such properties include a low number of crossings, large angles between edges, short edges, and depicting symmetries. Many of these properties are explicitly measurable metrics. This lets us model a graph-drawing problem as a game where a single player iteratively moves vertices of a straight-line graph drawing to reduce edge crossings. We investigate whether reinforcement learning can discover effective strategies for playing this game. Our reinforcement-learning agent observes the local geometric and structural context of a vertex and selects a movement direction with the goal of reducing either the global or the local crossing number, that is, either the total number of crossings or the maximum number of crossings per edge. We compare the resulting strategies to existing methods and established crossing-minimization heuristics on standard benchmark graphs. While our approach does not out-compete state-of-the-art methods for minimizing the global crossing number, it is competitive and often superior for minimizing the local crossing number.

Cite As Get BibTex

Timo Brand, Henry Förster, Stephen Kobourov, Daniel Kohrt, Robin Schukrafft, Markus Wallinger, and Johannes Zink. Using Reinforcement Learning to Optimize the Global and Local Crossing Number. In 34th International Symposium on Graph Drawing and Network Visualization (GD 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 396, pp. 24:1-24:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026) https://doi.org/10.4230/LIPIcs.GD.2026.24

Author Details

Timo Brand
  • Technical University of Munich, Heilbronn, Germany
Henry Förster
  • John Cabot University, Rome, Italy
Stephen Kobourov
  • Technical University of Munich, Heilbronn, Germany
Daniel Kohrt
  • Technical University of Munich, Garching, Germany
Robin Schukrafft
  • Technical University of Munich, Heilbronn, Germany
Markus Wallinger
  • Technical University of Munich, Heilbronn, Germany
Johannes Zink
  • Technical University of Munich, Heilbronn, Germany

Supplementary Materials

References

  1. Reyan Ahmed, Felice De Luca, Sabin Devkota, Stephen Kobourov, and Mingwei Li. Multicriteria scalable graph drawing via stochastic gradient descent, (SGD)². IEEE Transactions on Visualization and Computer Graphics, 28(6):2388-2399, 2022. URL: https://doi.org/10.1109/TVCG.2022.3155564.
  2. Réka Albert and Albert-László Barabási. Topology of evolving networks: local events and universality. Physical review letters, 85(24):5234, 2000. URL: https://doi.org/10.1103/physrevlett.85.5234.
  3. Evmorfia N. Argyriou, Michael A. Bekos, and Antonios Symvonis. Maximizing the total resolution of graphs. Comput. J., 56(7):887-900, 2013. URL: https://doi.org/10.1093/COMJNL/BXS088.
  4. Sara Di Bartolomeo, Tarik Crnovrsanin, David Saffo, Eduardo Puerta, Connor Wilson, and Cody Dunne. Evaluating graph layout algorithms: A systematic review of methods and best practices. Comput. Graph. Forum, 43(6), 2024. URL: https://doi.org/10.1111/CGF.15073.
  5. Carlo Batini, Maurizio Talamo, and Roberto Tamassia. Computer aided layout of entity relationship diagrams. J. Syst. Softw., 4(2-3):163-173, 1984. URL: https://doi.org/10.1016/0164-1212(84)90006-2.
  6. Michael A. Bekos, Henry Förster, Christian Geckeler, Lukas Holländer, Michael Kaufmann, Amadäus M. Spallek, and Jan Splett. A heuristic approach towards drawings of graphs with high crossing resolution. Comput. J., 64(1):7-26, 2021. URL: https://doi.org/10.1093/COMJNL/BXZ133.
  7. Daniel Bienstock. Some provably hard crossing number problems. Discrete & Computational Geometry, 6(3):443-459, 1991. URL: https://doi.org/10.1007/BF02574701.
  8. Timo Brand, Henry Förster, Stephen Kobourov, Daniel Kohrt, Robin Schukrafft, Markus Wallinger, and Johannes Zink. Using reinforcement learning to optimize the global and local crossing number. ArXiv preprint, CoRR, 2026. URL: https://arxiv.org/abs/2509.06108.
  9. Timo Brand, Henry Förster, Stephen Kobourov, Daniel Kohrt, Robin Schukrafft, Markus Wallinger, and Johannes Zink. RL 4 crossing reduction: code, data, models, results. https://github.com/j-zink-wuerzburg/rl-4-gd-crossing-reduction, 2026.
  10. Markus Chimani, Hanna Döring, and Matthias Reitzner. Crossing numbers and stress of random graphs. In Therese Biedl and Andreas Kerren, editors, Proc. 26th International Symposium on Graph Drawing and Network Visualization (GD 2018), volume 11282 of Lecture Notes in Computer Science, pages 255-268. Springer, 2018. URL: https://doi.org/10.1007/978-3-030-04414-5_18.
  11. Markus Chimani and Tilo Wiedera. An ILP-based proof system for the crossing number problem. In Piotr Sankowski and Christos D. Zaroliagis, editors, Proc. 24th Annual European Symposium on Algorithms (ESA2016), volume 57 of LIPIcs, pages 29:1-29:13. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2016. URL: https://doi.org/10.4230/LIPIcs.ESA.2016.29.
  12. P. David. AmzPlayer: A modern player for Zillions. http://www.polyomino.com/amzplayer/, 2023.
  13. Almut Demel, Dominik Dürrschnabel, Tamara Mchedlidze, Marcel Radermacher, and Lasse Wulf. A greedy heuristic for crossing-angle maximization. In Therese Biedl and Andreas Kerren, editors, Proc. 26th International Symposium on Graph Drawing and Network Visualization (GD 2018), volume 11282 of Lecture Notes in Computer Science, pages 286-299. Springer, 2018. URL: https://doi.org/10.1007/978-3-030-04414-5_20.
  14. Sabin Devkota, Abu Reyan Ahmed, Felice De Luca, Katherine E. Isaacs, and Stephen G. Kobourov. Stress-plus-X (SPX) graph layout. In Daniel Archambault and Csaba D. Tóth, editors, Proc. 27th International Symposium on Graph Drawing and Network Visualization (GD 2019), volume 11904 of Lecture Notes in Computer Science, pages 291-304. Springer, 2019. URL: https://doi.org/10.1007/978-3-030-35802-0_23.
  15. Giuseppe Di Battista, Ashim Garg, Giuseppe Liotta, Roberto Tamassia, Emanuele Tassinari, and Francesco Vargiu. An experimental comparison of four graph drawing algorithms. Computational Geometry, 7(5-6):303-325, 1997. URL: https://doi.org/10.1016/s0925-7721(96)00005-3.
  16. Walter Didimo, Giuseppe Liotta, and Fabrizio Montecchiani. A survey on graph drawing beyond planarity. ACM Comput. Surv., 52(1):4:1-4:37, 2019. URL: https://doi.org/10.1145/3301281.
  17. Walter Didimo, Giuseppe Liotta, and Salvatore Agostino Romeo. Topology-driven force-directed algorithms. In Ulrik Brandes and Sabine Cornelsen, editors, Proc. 18th International Symposium on Graph Drawing (GD 2010), volume 6502 of Lecture Notes in Computer Science, pages 165-176. Springer, 2010. URL: https://doi.org/10.1007/978-3-642-18469-7_15.
  18. Werner Duvaud and Aurèle Hainaut. Muzero general: Open reimplementation of muzero. https://github.com/werner-duvaud/muzero-general, 2019.
  19. Thomas M.J. Fruchterman and Edward M. Reingold. Graph drawing by force-directed placement. Software: Practice and experience, 21(11):1129-1164, 1991. URL: https://doi.org/10.1002/spe.4380211102.
  20. M. R. Garey and D. S. Johnson. Crossing number is NP-complete. SIAM Journal on Algebraic Discrete Methods, 4(3):312-316, 1983. URL: https://doi.org/10.1137/0604033.
  21. Loann Giovannangeli, Frédéric Lalanne, David Auber, Romain Giot, and Romain Bourqui. Deep neural network for drawing networks, (DNN)². In Helen C. Purchase and Ignaz Rutter, editors, Proc. 29th International Symposium on Graph Drawing and Network Visualization (GD 2021), volume 12868 of Lecture Notes in Computer Science, pages 375-390. Springer, 2021. URL: https://doi.org/10.1007/978-3-030-92931-2_27.
  22. Alexander Grigoriev and Hans L. Bodlaender. Algorithms for graphs embeddable with few crossings per edge. Algorithmica, 49(1):1-11, 2007. URL: https://doi.org/10.1007/S00453-007-0010-X.
  23. Aric Hagberg, Pieter J Swart, and Daniel A Schult. Exploring network structure, dynamics, and function using networkx. Technical report, Los Alamos National Laboratory (LANL), Los Alamos, NM (United States), 2008. Function used to generate extended Barabási-Albert graphs: URL: https://networkx.org/documentation/stable/reference/generated/networkx.generators.random_graphs.extended_barabasi_albert_graph.html.
  24. Weidong Huang, Peter Eades, Seok-Hee Hong, and Chun-Cheng Lin. Improving multiple aesthetics produces better graph drawings. J. Vis. Lang. Comput., 24(4):262-272, 2013. URL: https://doi.org/10.1016/J.JVLC.2011.12.002.
  25. Tomihisa Kamada and Satoru Kawai. An algorithm for drawing general undirected graphs. Information Processing Letters, 31(1):7-15, 1989. URL: https://doi.org/10.1016/0020-0190(89)90102-6.
  26. Stephen G. Kobourov, Giuseppe Liotta, and Fabrizio Montecchiani. An annotated bibliography on 1-planarity. Comput. Sci. Rev., 25:49-67, 2017. URL: https://doi.org/10.1016/J.COSREV.2017.06.002.
  27. Vladimir P. Korzhik and Bojan Mohar. Minimal obstructions for 1-immersions and hardness of 1-planarity testing. In Ioannis G. Tollis and Maurizio Patrignani, editors, Proc. 16th International Symposium on Graph Drawing (GD 2008), volume 5417 of Lecture Notes in Computer Science, pages 302-312. Springer, 2008. URL: https://doi.org/10.1007/978-3-642-00219-9_29.
  28. Vladimir P. Korzhik and Bojan Mohar. Minimal obstructions for 1-immersions and hardness of 1-planarity testing. J. Graph Theory, 72(1):30-71, 2013. URL: https://doi.org/10.1002/JGT.21630.
  29. Oh-Hyun Kwon and Kwan-Liu Ma. A deep generative model for graph layout. IEEE Trans. Vis. Comput. Graph., 26(1):665-675, 2020. URL: https://doi.org/10.1109/TVCG.2019.2934396.
  30. Marc Lanctot, Edward Lockhart, Jean-Baptiste Lespiau, Vinicius Zambaldi, Satyaki Upadhyay, Julien Pérolat, Sriram Srinivasan, Finbarr Timbers, Karl Tuyls, Shayegan Omidshafiei, Daniel Hennes, Dustin Morrill, Paul Muller, Timo Ewalds, Ryan Faulkner, János Kramár, Bart De Vylder, Brennan Saeta, James Bradbury, David Ding, Sebastian Borgeaud, Matthew Lai, Julian Schrittwieser, Thomas Anthony, Edward Hughes, Ivo Danihelka, and Jonah Ryan-Davis. OpenSpiel: A framework for reinforcement learning in games. ArXiv preprint, CoRR, 2019. URL: https://arxiv.org/abs/1908.09453.
  31. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin A. Riedmiller, Andreas Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. Human-level control through deep reinforcement learning. Nature, 518(7540):529-533, 2015. URL: https://doi.org/10.1038/NATURE14236.
  32. OpenAI, Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemysław Dębiak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Chris Hesse, Rafal Józefowicz, Scott Gray, Catherine Olsson, Jakub Pachocki, Michael Petrov, Henrique Pondé de Oliveira Pinto, Jonathan Raiman, Tim Salimans, Jeremy Schlatter, Jonas Schneider, Szymon Sidor, Ilya Sutskever, Jie Tang, Filip Wolski, and Susan Zhang. Dota 2 with large scale deep reinforcement learning. ArXiv preprint, CoRR, 2019. URL: https://arxiv.org/abs/1912.06680.
  33. Maximilian Pfister. Personal communication, 2025. Google Scholar
  34. Helen C. Purchase. Effective information visualisation: a study of graph drawing aesthetics and algorithms. Interacting with Computers, 13(2):147-162, 2000. URL: https://doi.org/10.1016/S0953-5438(00)00032-1.
  35. Helen C. Purchase, David A. Carrington, and Jo-Anne Allder. Empirical evaluation of aesthetics-based graph layout. Empirical Software Engineering, 7(3):233-255, 2002. URL: https://doi.org/10.1023/A:1016344215610.
  36. Marcel Radermacher, Klara Reichard, Ignaz Rutter, and Dorothea Wagner. Geometric heuristics for rectilinear crossing minimization. ACM J. Exp. Algorithmics, 24(1):1.12:1-1.12:21, 2019. URL: https://doi.org/10.1145/3325861.
  37. Ilkin Safarli, Youjia Zhou, and Bei Wang. Interpreting graph drawing with multi-agent reinforcement learning. ArXiv preprint, CoRR, 2020. URL: https://arxiv.org/abs/2011.00748.
  38. Marcus Schaefer. The graph crossing number and its variants: A survey. The Electronic Journal of Combinatorics, 2013 (last updated in 2024). URL: https://doi.org/10.37236/2713.
  39. Marcus Schaefer. Complexity of geometric k-planarity for fixed k. J. Graph Algorithms Appl., 25(1):29-41, 2021. URL: https://doi.org/10.7155/JGAA.00548.
  40. Marcus Schaefer. On the complexity of some geometric problems with fixed parameters. J. Graph Algorithms Appl., 25(1):195-218, 2021. URL: https://doi.org/10.7155/JGAA.00557.
  41. Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre, Simon Schmitt, Arthur Guez, Edward Lockhart, Demis Hassabis, Thore Graepel, Timothy P. Lillicrap, and David Silver. Mastering Atari, Go, chess and shogi by planning with a learned model. Nature, 588(7839):604-609, 2020. URL: https://doi.org/10.1038/S41586-020-03051-4.
  42. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms. ArXiv preprint, CoRR, 2017. URL: https://arxiv.org/abs/1707.06347.
  43. David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Vedavyas Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy P. Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, and Demis Hassabis. Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587):484-489, 2016. URL: https://doi.org/10.1038/NATURE16961.
  44. David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, and Demis Hassabis. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, 362(6419):1140-1144, 2018. URL: https://doi.org/10.1126/science.aar6404.
  45. David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy P. Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel, and Demis Hassabis. Mastering the game of Go without human knowledge. Nature, 550(7676):354-359, 2017. URL: https://doi.org/10.1038/NATURE24270.
  46. Stephen Tavener. Ai Ai: a Java-based general game playing engine. http://mrraow.com/index.php/aiai-home/, 2025.
  47. Theoretical Computer Science Group, University of Osnabrück. Crossing number - Rome graphs: Exact crossing numbers. https://tcs.uos.de/doku.php?id=research/cr#rome_graphsexact_crossing_numbers, 2025.
  48. Xiaoqi Wang, Kevin Yen, Yifan Hu, and Han-Wei Shen. DeepGD: A deep learning framework for graph drawing using GNN. IEEE Computer Graphics and Applications, 41(5):32-44, 2021. URL: https://doi.org/10.1109/MCG.2021.3093908.
  49. Xiaoqi Wang, Kevin Yen, Yifan Hu, and Han-Wei Shen. SmartGD: A GAN-based graph drawing framework for diverse aesthetic goals. IEEE Transactions on Visualization and Computer Graphics, 30(8):5666-5678, 2023. URL: https://doi.org/10.1109/tvcg.2023.3306356.
  50. Yong Wang, Zhihua Jin, Qianwen Wang, Weiwei Cui, Tengfei Ma, and Huamin Qu. Deepdrawing: A deep learning approach to graph drawing. IEEE Trans. Vis. Comput. Graph., 26(1):676-686, 2020. URL: https://doi.org/10.1109/TVCG.2019.2934798.
  51. Colin Ware, Helen C. Purchase, Linda Colpoys, and Matthew McGill. Cognitive measurements of graph aesthetics. Information Visualization, 1(2):103-110, 2002. URL: https://doi.org/10.1057/palgrave.ivs.9500013.
  52. Christopher J. C. H. Watkins and Peter Dayan. Q-learning (technical note). Mach. Learn., 8:279-292, 1992. URL: https://doi.org/10.1007/BF00992698.
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact