{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:23:22Z","timestamp":1785421402197,"version":"3.56.0"},"reference-count":73,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T00:00:00Z","timestamp":1625011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2021,6,30]]},"abstract":"<jats:p>Generative Adversarial Networks (GANs) are difficult to train because of pathologies such as mode and discriminator collapse. Similar pathologies have been studied and addressed in competitive evolutionary computation by increased diversity. We study a system, Lipizzaner, that combines spatial coevolution with gradient-based learning to improve the robustness and scalability of GAN training. We study different features of Lipizzaner\u2019s evolutionary computation methodology. Our ablation experiments determine that communication, selection, parameter optimization, and ensemble optimization each, as well as in combination, play critical roles. Lipizzaner succumbs less frequently to critical collapses and, as a side benefit, demonstrates improved performance. In addition, we show a GAN-training feature of Lipizzaner: the ability to train simultaneously with different loss functions in the gradient descent parameter learning framework of each GAN at each cell. We use an image generation problem to show that different loss function combinations result in models with better accuracy and more diversity in comparison to other existing evolutionary GAN models. Finally, Lipizzaner with multiple loss function options promotes the best model diversity while requiring a large grid size for adequate accuracy.<\/jats:p>","DOI":"10.1145\/3458845","type":"journal-article","created":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T14:57:04Z","timestamp":1627570624000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Spatial Coevolution for Generative Adversarial Network Training"],"prefix":"10.1145","volume":"1","author":[{"given":"Erik","family":"Hemberg","sequence":"first","affiliation":[{"name":"MIT CSAIL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamal","family":"Toutouh","sequence":"additional","affiliation":[{"name":"MIT CSAIL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdullah","family":"Al-Dujaili","sequence":"additional","affiliation":[{"name":"MIT CSAIL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Schmiedlechner","sequence":"additional","affiliation":[{"name":"MIT CSAIL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Una-May","family":"O\u2019Reilly","sequence":"additional","affiliation":[{"name":"MIT CSAIL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,29]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the AAAI Fall Symposium. arXiv preprint arXiv:1807","author":"Al-Dujaili Abdullah","year":"2018"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of the International Workshop on Global Optimization.","author":"Al-Dujaili Abdullah","year":"2018"},{"key":"e_1_2_1_3_1","volume-title":"Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862","author":"Arjovsky Martin","year":"2017"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305404"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305405"},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Arora Sanjeev","year":"2018"},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of the Congress on Evolutionary Computation. IEEE, 1605\u20131611","author":"Barbosa Helio J. C.","year":"1999"},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the International Conference on Genetic Algorithms.","author":"Barbosa Helio J. C.","year":"1997"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.009"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the International Conference on Parallel Problem Solving from Nature. Springer, 144\u2013153","author":"Branke J\u00fcrgen","year":"2008"},{"key":"e_1_2_1_11_1","unstructured":"Jason Brownlee. 2019. Generative Adversarial Networks with Python Deep Learning Generative Models for Image Synthesis and Image Translation. Machine Learning Mastery.  Jason Brownlee. 2019. Generative Adversarial Networks with Python Deep Learning Generative Models for Image Synthesis and Image Translation. Machine Learning Mastery."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103946"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9407\u20139415","author":"Chavdarova Tatjana","year":"2018"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08600-2"},{"key":"e_1_2_1_15_1","unstructured":"Soumith Chintala Emily Denton Martin Arjovsky and Michael Mathieu. 2016. How to train a GAN? Tips and tricks to make GANs work. Retrieved from https:\/\/github.com\/soumith\/ganhacks.  Soumith Chintala Emily Denton Martin Arjovsky and Michael Mathieu. 2016. How to train a GAN? Tips and tricks to make GANs work. Retrieved from https:\/\/github.com\/soumith\/ganhacks."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/645300.648375"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the International Conference on the Applications of Evolutionary Computation. Springer, 473\u2013487","author":"Costa Victor","year":"2019"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/1457317"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2008.920671"},{"key":"e_1_2_1_20_1","volume-title":"NIPS 2016 tutorial: Generative adversarial networks. arXiv preprint arXiv:1701","author":"Goodfellow Ian","year":"2016"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-014-9224-2"},{"key":"e_1_2_1_23_1","volume-title":"Proceedings of the Congress on Evolutionary Computation","volume":"2","author":"Herrmann Jeffrey W.","year":"1999"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295408"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295408"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(90)90076-2"},{"key":"e_1_2_1_27_1","doi-asserted-by":"crossref","volume-title":"Maintenance of a long running distributed genetic programming system for solving problems requiring big data","author":"Hodjat Babak","DOI":"10.1007\/978-1-4939-0375-7_4"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/648159.749853"},{"key":"e_1_2_1_29_1","volume-title":"et\u00a0al","author":"Jaderberg Max","year":"2017"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/982409.982427"},{"key":"e_1_2_1_31_1","volume-title":"Chris Dongjoo Kim, and Graham Taylor","author":"Im Daniel Jiwoong","year":"2016"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2005.856208"},{"key":"e_1_2_1_33_1","first-page":"3","article-title":"Optimal experiment design for coevolutionary active learning","volume":"18","author":"Ly Daniel Le","year":"2014","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"e_1_2_1_34_1","unstructured":"Yann LeCun. 1998. The MNIST database of handwritten digits. Retrieved from http:\/\/yann. lecun. com\/exdb\/mnist\/.  Yann LeCun. 1998. The MNIST database of handwritten digits. Retrieved from http:\/\/yann. lecun. com\/exdb\/mnist\/."},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the International Conference on Artificial Neural Networks. Springer, 604\u2013619","author":"Lesort Timoth\u00e9e","year":"2019"},{"key":"e_1_2_1_36_1","volume-title":"Distributional adversarial networks. arXiv preprint arXiv:1706.09549","author":"Li Chengtao","year":"2017"},{"key":"e_1_2_1_37_1","volume-title":"Towards understanding the dynamics of generative adversarial networks. arXiv preprint arXiv:1706.09884","author":"Li Jerry","year":"2017"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 4512\u20134521","author":"Lin Chieh Hubert","year":"2019"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327008"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"e_1_2_1_43_1","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/TEVC.2017.2767023","article-title":"Coevolutionary multiobjective evolutionary algorithms: Survey of the state-of-the-art","volume":"22","author":"Miguel Antonio L.","year":"2018","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"e_1_2_1_44_1","first-page":"137","article-title":"Coevolutionary learning with spatially distributed populations","volume":"400","author":"Mitchell Melanie","year":"2006","journal-title":"Comput. Intell.: Princ. Pract."},{"key":"e_1_2_1_45_1","volume-title":"Artificial Life Conference Proceedings. The MIT Press, 39\u201346","author":"Moran Nick","year":"2018"},{"key":"e_1_2_1_46_1","volume-title":"Dropout-GAN: Learning from a dynamic ensemble of discriminators. arXiv preprint arXiv:1807.11346","author":"Mordido Gon\u00e7alo","year":"2018"},{"key":"e_1_2_1_47_1","volume-title":"Stabilizing GAN training with multiple random projections. arXiv preprint arXiv:1705.07831","author":"Neyshabur Behnam","year":"2017"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295027"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1162\/106454698568620"},{"key":"e_1_2_1_50_1","volume-title":"De Jong","author":"Popovici Elena","year":"2012"},{"key":"e_1_2_1_51_1","first-page":"1355","article-title":"A new differential evolution algorithm for minimax optimization in robust design","volume":"48","author":"Qiu Xin","year":"2017","journal-title":"IEEE Trans. Cyber."},{"key":"e_1_2_1_52_1","volume-title":"Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434","author":"Radford Alec","year":"2015"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1162\/evco.1997.5.1.1"},{"key":"e_1_2_1_54_1","volume-title":"Evolution strategies as a scalable alternative to reinforcement learning. arXiv:1703.03864","author":"Salimans Tim","year":"2017"},{"key":"e_1_2_1_55_1","volume-title":"Industrial-scale Evolutionary Machine Learning. Master\u2019s thesis","author":"Schmiedlechner Tom"},{"key":"e_1_2_1_56_1","volume-title":"Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS\u201918) Workshop on Systems for ML and Open Source Software.arXiv preprint arXiv:1811","author":"Schmiedlechner Tom","year":"2018"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_14"},{"key":"e_1_2_1_58_1","volume-title":"Stanley and Jeff Clune","author":"Kenneth","year":"2017"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0006-z"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"e_1_2_1_61_1","volume-title":"Evaluating text GANs as language models. arXiv preprint arXiv:1810.12686","author":"Tevet Guy","year":"2018"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295294"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321860"},{"key":"e_1_2_1_64_1","volume-title":"Deep Neural Evolution","author":"Toutouh Jamal"},{"key":"e_1_2_1_65_1","volume-title":"Coulomb GANs: Provably optimal Nash equilibria via potential fields. arXiv preprint arXiv:1708.08819","author":"Unterthiner Thomas","year":"2017"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2895748"},{"key":"e_1_2_1_67_1","volume-title":"Ensembles of generative adversarial networks. arXiv preprint arXiv:1612.00991","author":"Wang Yaxing","year":"2016"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.5555\/2955239.2955343"},{"key":"e_1_2_1_69_1","volume-title":"Proceedings of the IEEE Congress on Evolutionary Computation (CEC\u201908)","author":"Wierstra Daan","year":"2008"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/1068009.1068096"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146355"},{"key":"e_1_2_1_72_1","volume-title":"Consistency regularization for generative adversarial networks. arXiv preprint arXiv:1910.12027","author":"Zhang Han","year":"2019"},{"key":"e_1_2_1_73_1","volume-title":"Dynamic cooperative coevolution for large scale optimization","author":"Zhang Xin-Yuan","year":"2019"},{"key":"e_1_2_1_74_1","volume-title":"Energy-based generative adversarial network. arXiv preprint arXiv:1609.03126","author":"Zhao Junbo","year":"2016"}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3458845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:22Z","timestamp":1750191142000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,30]]},"references-count":73,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,6,30]]}},"alternative-id":["10.1145\/3458845"],"URL":"https:\/\/doi.org\/10.1145\/3458845","relation":{},"ISSN":["2688-299X","2688-3007"],"issn-type":[{"value":"2688-299X","type":"print"},{"value":"2688-3007","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,30]]},"assertion":[{"value":"2019-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}