{"type":"ScholarlyArticle","title":"GIDnets: Generative Neural Networks for Solving Inverse Design Problems via Latent Space Exploration","authors":[{"name":"Carlo Adornetto","slug":"carlo-adornetto","given":"Carlo","family":"Adornetto","affiliation":"University of Calabria"},{"name":"Gianluigi Greco","slug":"gianluigi-greco","given":"Gianluigi","family":"Greco","affiliation":"University of Calabria"}],"abstract":"In a number of different fields, including Engeneering, Chemistry and Physics, the design of technological tools and device structures is increasingly supported by deep-learning based methods, which provide suggestions on crucial architectural choices based on the properties that these tools and structures should exhibit. The paper proposes a novel architecture, named GIDnet, to address this inverse design problem, which is based on exploring a suitably defined latent space associated with the possible designs. Among its distinguishing features, GIDnet is capable of identifying the most appropriate starting point for the exploration and of likely converging into a point corresponding to a design that is a feasible one. Results of a thorough experimental activity evidence that GIDnet outperforms earlier approaches in the literature.","doi":"10.24963/ijcai.2023/379","url":"https://ijcai.org/proceedings/2023/379","pdf":"https://ijcai.org/proceedings/2023/0379.pdf","markdown":"https://ijcai.org/proceedings/2023/379.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/379","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":379,"pages":{"first":3404,"last":3413},"keywords":["Machine Learning: ML: Experimental methodology","Machine Learning: ML: Autoencoders","Machine Learning: ML: Applications"],"videos":[],"references":[{"position":1,"raw":"[Asano and Noda, 2018] Takashi Asano and Susumu Noda. Optimization of photonic crystal nanocavities based on deep learning. Optics Express, 26(25):32704-32717, 2018.","title":"Optimization of photonic crystal nanocavities based on deep learning","authors":"Noda ; ] Takashi Asano, Susumu Asano, Noda","year":"2018","venue":"Optics Express","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Banerjee et al., 2021] Chaity Banerjee, Chad Lilian, Daniel Reasor, Eduardo Pasiliao, and Tathagata Mukherjee. An application of generative adversarial networks for robust inference in computational fluid dynamics. In Proc. of ICISDM'21, page 74-83, 2021.","title":"An application of generative adversarial networks for robust inference in computational fluid dynamics","authors":"Banerjee","year":"2021","venue":"Proc. of ICISDM'21","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2019] Yingshi Chen, Jinfeng Zhu, Yinong Xie, Naixing Feng, and Qing Huo Liu. Smart inverse design of graphene-based photonic metamaterials by an adaptive artificial neural network. Nanoscale, 11(19):9749-9755, 2019.","title":"Smart inverse design of graphene-based photonic metamaterials by an adaptive artificial neural network","authors":"Chen","year":"2019","venue":"Nanoscale","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chiarello et al., 2021] Filippo Chiarello, Paola Belingheri, and Gualtiero Fantoni. Data science for engineering de- sign: State of the art and future directions. Computers in Industry, 129:103447, 2021.","title":"Data science for engineering design: State of the art and future directions","authors":"Filippo Chiarello, Paola Belingheri, Gualtiero Fantoni","year":"2021","venue":"Computers in Industry","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chilwell and Hodgkinson, 1984] John Chilwell and Ian Hodgkinson. Thin-films field-transfer matrix theory of planar multilayer waveguides and reflection from prism- loaded waveguides. Journal of the Optical Society of America, A, 1(7):742-753, 1984.","title":"John Chilwell and Ian Hodgkinson. Thin-films field-transfer matrix theory of planar multilayer waveguides and reflection from prismloaded waveguides","authors":"Hodgkinson Chilwell","year":"1984","venue":"Journal of the Optical Society of America, A","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Coli et al., 2022] Gabriele M. Coli, Emanuele Boattini, Laura Filion, and Marjolein Dijkstra. Inverse design of soft materials via a deep learning-based evolutionary strat- egy. Science Advances, 8(3):eabj6731, 2022.","title":"Inverse design of soft materials via a deep learning-based evolutionary strategy","authors":"Gabriele M Coli, Emanuele Boattini, Laura Filion, Marjolein Dijkstra","year":"2022","venue":"Science Advances","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Debnath et al., 2021] Arindam Debnath, Adam M Krajew- ski, Hui Sun, Shuang Lin, Marcia Ahn, Wenjie Li, Shan- shank Priya, Jogender Singh, Shunli Shang, Allison M Beese, et al. Generative deep learning as a tool for in- verse design of high entropy refractory alloys. Journal of Materials Informatics, 1(1):3, 2021.","title":"Generative deep learning as a tool for inverse design of high entropy refractory alloys","authors":"Arindam Debnath, Adam M Krajewski, Hui Sun, Shuang Lin, Marcia Ahn, Wenjie Li, Shanshank Priya, Jogender Singh, Shunli Shang, Allison M Beese","year":"2021","venue":"Journal of Materials Informatics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dodaro et al., 2022] Carmine Dodaro, Valeria Fionda, and Gianluigi Greco. LTL on weighted finite traces: Formal foundations and algorithms. In Proc. of IJCAI'22, pages 2606-2612, 2022.","title":"LTL on weighted finite traces: Formal foundations and algorithms","authors":"Carmine Dodaro, Valeria Fionda, Gianluigi Greco","year":"2022","venue":"Proc. of IJCAI'22","doi":null,"url":null,"internal_url":"/proceedings/2022/361"},{"position":9,"raw":"[Glotzer, 2021] Sharon C. Glotzer. Data science for assem- bly engineering. In Proc. of KDD'21, page 2, 2021.","title":"Data science for assembly engineering","authors":"Sharon C Glotzer","year":"2021","venue":"Proc. of KDD'21","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Grantham et al., 2022] Karl Grantham, Muhetaer Mukaidaisi, Hsu Kiang Ooi, Mohammad Sajjad Ghaemi, Alain Tchagang, and Yifeng Li. Deep evolutionary learning for molecular design. IEEE Computational Intelligence Magazine, 17(2):14-28, 2022.","title":"Deep evolutionary learning for molecular design","authors":"Karl Grantham, Muhetaer Mukaidaisi, Kiang Hsu, Mohammad Sajjad Ooi, Alain Ghaemi, Yifeng Tchagang, Li","year":"2022","venue":"IEEE Computational Intelligence Magazine","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Greco et al., 2015] Gianluigi Greco, Antonella Guzzo, Francesco Lupia, and Luigi Pontieri. Process discov- ery under precedence constraints. ACM Transactions on Knowledge Discovery from Data, 9(4), 2015.","title":"Process discovery under precedence constraints","authors":"Gianluigi Greco, Antonella Guzzo, Francesco Lupia, Luigi Pontieri","year":"2015","venue":"ACM Transactions on Knowledge Discovery from Data","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gómez-Bombarelli et al., 2018] Rafael Gómez- Bombarelli, Jennifer N. Wei, David Duvenaud, José Miguel Hernández-Lobato, Benjamín Sánchez- Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D. Hirzel, Ryan P. Adams, and Alán Aspuru- Guzik. Automatic chemical design using a data-driven continuous representation of molecules. ACS Central Science, 4(2):268-276, 2018. PMID: 29532027.","title":"Automatic chemical design using a data-driven continuous representation of molecules","authors":"Rafael Gómez-Bombarelli, Jennifer N Wei, David Duvenaud, José Miguel Hernández-Lobato, Benjamín Sánchez-Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D Hirzel, Ryan P Adams, Alán Aspuru-Guzik","year":"2018","venue":"ACS Central Science","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Heyrani Nobari et al., 2021] Amin Heyrani Nobari, Wei Chen, and Faez Ahmed. Pcdgan: A continuous conditional diverse generative adversarial network for inverse design. In Proc. of KDD'21, page 606-616, 2021.","title":"Pcdgan: A continuous conditional diverse generative adversarial network for inverse design","authors":"Amin Heyrani, Nobari, Wei Chen, Faez Ahmed","year":"2021","venue":"Proc. of KDD'21","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Jiang and Fan, 2019] Jiaqi Jiang and Jonathan A. Fan. Global optimization of dielectric metasurfaces using a physics-driven neural network. Nano Letters, 19(8):5366- 5372, 2019.","title":"Global optimization of dielectric metasurfaces using a physics-driven neural network","authors":"Jiaqi Jiang, Jonathan A Fan","year":"2019","venue":"Nano Letters","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Jiang et al., 2019] Jiaqi Jiang, David Sell, Stephan Hoyer, Jason Hickey, Jianji Yang, and Jonathan A. Fan. Free- form diffractive metagrating design based on generative adversarial networks. ACS Nano, 13(8):8872-8878, 2019.","title":"Freeform diffractive metagrating design based on generative adversarial networks","authors":"Jiaqi Jiang, David Sell, Stephan Hoyer, Jason Hickey, Jianji Yang, Jonathan A Fan","year":"2019","venue":"ACS Nano","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Jiang et al., 2020] Jiaqi Jiang, Mingkun Chen, and Jonathan A. Fan. Deep neural networks for the evalu- ation and design of photonic devices. Nature Reviews Materials, 2020.","title":"Deep neural networks for the evaluation and design of photonic devices","authors":"Jiaqi Jiang, Mingkun Chen, Jonathan A Fan","year":"2020","venue":"Nature Reviews Materials","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kruse et al., 2021] Jakob Kruse, Lynton Ardizzone, Carsten Rother, and Ullrich Köthe. Benchmarking invert- ible architectures on inverse problems. arXiv preprint arXiv:2101.10763, 2021.","title":"Benchmarking invertible architectures on inverse problems","authors":"Kruse","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lininger et al., 2021] Andrew Lininger, Michael Hinczewski, and Giuseppe Strangi. General inverse design of layered thin-film materials with convolutional neural networks. ACS Photonics, 8(12):3641-3650, 2021.","title":"General inverse design of layered thin-film materials with convolutional neural networks","authors":"Andrew Lininger, Michael Hinczewski, Giuseppe Strangi","year":"2021","venue":"ACS Photonics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Liu et al., 2018a] Dianjing Liu, Yixuan Tan, Erfan Khoram, and Zongfu Yu. Training deep neural networks for the inverse design of nanophotonic structures. ACS Photonics, 5(4):1365-1369, 2018.","title":"Training deep neural networks for the inverse design of nanophotonic structures","authors":"Liu","year":"2018","venue":"ACS Photonics","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Liu et al., 2018b] Zhaocheng Liu, Dayu Zhu, Sean P. Ro- drigues, Kyu-Tae Lee, and Wenshan Cai. Generative model for the inverse design of metasurfaces. Nano Let- ters, 18(10):6570-6576, 2018.","title":"Generative model for the inverse design of metasurfaces","authors":"Liu","year":"2018","venue":"Nano Letters","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ma et al., 2019] Wei Ma, Feng Cheng, Yihao Xu, Qinlong Wen, and Yongmin Liu. Probabilistic representation and inverse design of metamaterials based on a deep generative model with semi-supervised learning strategy. Advanced Materials, 31(35):1901111, 2019.","title":"Probabilistic representation and inverse design of metamaterials based on a deep generative model with semi-supervised learning strategy","authors":"Wei Ma, Feng Cheng, Yihao Xu, Qinlong Wen, Yongmin Liu","year":"2019","venue":"Advanced Materials","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mahynski et al., 2020] Nathan A Mahynski, Runfang Mao, Evan Pretti, Vincent K Shen, and Jeetain Mittal. Grand canonical inverse design of multicomponent colloidal crystals. Soft Matter, 16(13):3187-3194, 2020.","title":"Grand canonical inverse design of multicomponent colloidal crystals","authors":"Runfang Nathan A Mahynski, Evan Mao, Pretti, Jeetain Vincent K Shen, Mittal","year":"2020","venue":"Soft Matter","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Mirza and Osindero, 2014] Mehdi Mirza and Simon Osin- dero. Conditional generative adversarial nets. CoRR, abs/1411.1784, 2014.","title":"Conditional generative adversarial nets","authors":"Mehdi Mirza, Simon Osindero","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Molesky et al., 2018] Sean Molesky, Zin Lin, Alexander Y Piggott, Weiliang Jin, Jelena Vucković, and Alejandro W Rodriguez. Inverse design in nanophotonics. Nature Pho- tonics, 12(11):659-670, 2018.","title":"Inverse design in nanophotonics","authors":"Sean Molesky, Zin Lin, Alexander Y Piggott, Weiliang Jin, Jelena Vucković, Alejandro W Rodriguez","year":"2018","venue":"Nature Photonics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Nellippallil et al., 2017] Anand Balu Nellippallil, Kevin N Song, Chung-Hyun Goh, Pramod Zagade, BP Gautham, Janet K Allen, and Farrokh Mistree. A goal-oriented, se- quential, inverse design method for the horizontal integra- tion of a multistage hot rod rolling system. Journal of Me- chanical Design, 139(3):031403, 2017.","title":"A goal-oriented, sequential, inverse design method for the horizontal integration of a multistage hot rod rolling system","authors":"Anand Balu Nellippallil, Kevin N Song, Chung-Hyun Goh, Pramod Zagade, Janet K Gautham, Farrokh Allen, Mistree","year":"2017","venue":"Journal of Mechanical Design","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Noh et al., 2020] Juhwan Noh, Geun Ho Gu, Sungwon Kim, and Yousung Jung. Machine-enabled inverse de- sign of inorganic solid materials: promises and challenges. Chemical Science, 11(19):4871-4881, 2020.","title":"Machine-enabled inverse design of inorganic solid materials: promises and challenges","authors":"Noh","year":"2020","venue":"Chemical Science","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Peurifoy et al., 2018] John Peurifoy, Yichen Shen, Li Jing, Yi Yang, Fidel Cano-Renteria, Brendan G. DeLacy, John D. Joannopoulos, Max Tegmark, and Marin Soljačić. Nanophotonic particle simulation and inverse design using artificial neural networks. Science Advances, 4(6):eaar4206, 2018.","title":"Nanophotonic particle simulation and inverse design using artificial neural networks","authors":"John Peurifoy, Yichen Shen, Li Jing, Yi Yang, Fidel Cano-Renteria, Brendan G Delacy, John D Joannopoulos, Max Tegmark, Marin Soljačić","year":"2018","venue":"Science Advances","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Ren et al., 2020] Simiao Ren, Willie Padilla, and Jordan Malof. Benchmarking deep inverse models over time, and the neural-adjoint method. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 38-48.","title":"Benchmarking deep inverse models over time, and the neural-adjoint method","authors":"Ren","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"Curran Associates, Inc., 2020.","title":null,"authors":"Curran Associates, Inc","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Ren et al., 2022] Simiao Ren, Ashwin Mahendra, Omar Khatib, Yang Deng, Willie J. Padilla, and Jordan M. Malof. Inverse deep learning methods and benchmarks for artificial electromagnetic material design. Nanoscale, 14:3958-3969, 2022.","title":"Inverse deep learning methods and benchmarks for artificial electromagnetic material design","authors":"Ren","year":"2022","venue":"Nanoscale","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Sekar et al., 2019] Vinothkumar Sekar, Mengqi Zhang, Chang Shu, and Boo Cheong Khoo. Inverse design of airfoil using a deep convolutional neural network. Aiaa Journal, 57(3):993-1003, 2019.","title":"Inverse design of airfoil using a deep convolutional neural network","authors":"Sekar","year":"2019","venue":"Aiaa Journal","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Sridharan et al., 2022] Bhuvanesh Sridharan, Manan Goel, and U. Deva Priyakumar. Modern machine learning for tackling inverse problems in chemistry: molecular design to realization. Chemical Comm., 58:5316-5331, 2022.","title":"Modern machine learning for tackling inverse problems in chemistry: molecular design to realization","authors":"Bhuvanesh Sridharan, Manan Goel, U Deva Priyakumar","year":"2022","venue":"Chemical Comm","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Unni et al., 2021] Rohit Unni, Kan Yao, Xizewen Han, Mingyuan Zhou, and Yuebing Zheng. A mixture-density- based tandem optimization network for on-demand in- verse design of thin-film high reflectors. Nanophotonics, 10(16):4057-4065, 2021.","title":"A mixture-densitybased tandem optimization network for on-demand inverse design of thin-film high reflectors","authors":"Rohit Unni, Kan Yao, Xizewen Han, Mingyuan Zhou, Yuebing Zheng","year":"2021","venue":"Nanophotonics","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wiecha et al., 2021] Peter R. Wiecha, Arnaud Arbouet, Christian Girard, and Otto L. Muskens. Deep learning in nano-photonics: inverse design and beyond. Photonic Re- search, 9(5):B182-B200, 2021.","title":"Deep learning in nano-photonics: inverse design and beyond","authors":"R Peter, Arnaud Wiecha, Christian Arbouet, Otto L Girard, Muskens","year":"2021","venue":"Photonic Research","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yeung et al., 2021] Christopher Yeung, Ju-Ming Tsai, Brian King, Benjamin Pham, David Ho, Julia Liang, Mark W. Knight, and Aaswath P. Raman. Multiplexed supercell metasurface design and optimization with tandem residual networks. Nanophotonics, 10(3):1133-1143, 2021.","title":"Multiplexed supercell metasurface design and optimization with tandem residual networks","authors":"Christopher Yeung, Ju-Ming Tsai, Brian King, Benjamin Pham, David Ho, Julia Liang, Mark W Knight, Aaswath P Raman","year":"2021","venue":"Nanophotonics","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zaabab et al., 1995] A.H. Zaabab, Qi-Jun Zhang, and M. Nakhla. A neural network modeling approach to cir- cuit optimization and statistical design. IEEE Transactions on Microwave Theory and Techniques, 43(6):1349-1358, 1995.","title":"A neural network modeling approach to circuit optimization and statistical design","authors":"A H Zaabab, Qi-Jun Zhang, M Nakhla","year":"1995","venue":"IEEE Transactions on Microwave Theory and Techniques","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhang et al., 2018] C. Zhang, J. Jin, W. Na, Q. Zhang, and M. Yu. Multivalued neural network inverse modeling and applications to microwave filters. IEEE Trans. on Mi- crowave Theory and Techniques, 66(8):3781-3797, 2018.","title":"Multivalued neural network inverse modeling and applications to microwave filters","authors":"C Zhang, J Jin, W Na, Q Zhang, M Yu","year":"2018","venue":"IEEE Trans. on Microwave Theory and Techniques","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}