{"type":"ScholarlyArticle","title":"Unified Model for Crystalline Material Generation","authors":[{"name":"Astrid Klipfel","slug":"astrid-klipfel","given":"Astrid","family":"Klipfel","affiliation":"Univ. Artois , UMR 8188 , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France.; Univ. Artois , UMR 8181 , Unité de Catalyse et de Chimie du Solide (UCCS) , F-62300 Lens , France.; Univ. Artois , UR 2462 , Laboratoire de Mathématiques de Lens (LML) , F-62300 Lens , France."},{"name":"Yaël Frégier","slug":"yael-fregier","given":"Yaël","family":"Frégier","affiliation":"Univ. Artois , UR 2462 , Laboratoire de Mathématiques de Lens (LML) , F-62300 Lens , France."},{"name":"Adlane Sayede","slug":"adlane-sayede","given":"Adlane","family":"Sayede","affiliation":"Univ. Artois , UMR 8181 , Unité de Catalyse et de Chimie du Solide (UCCS) , F-62300 Lens , France."},{"name":"Zied Bouraoui","slug":"zied-bouraoui","given":"Zied","family":"Bouraoui","affiliation":"Univ. Artois , UMR 8188 , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France."}],"abstract":"One of the greatest challenges facing our society is the discovery of new innovative crystal materials with specific properties. Recently, the problem of generating crystal materials has received increasing attention, however, it remains unclear to what extent, or in what way, we can develop generative models that consider both the periodicity and equivalence geometric of crystal structures. To alleviate this issue, we propose two unified models that act at the same time on crystal lattice and atomic positions using periodic equivariant architectures. Our models are capable to learn any arbitrary crystal lattice deformation by lowering the total energy to reach thermodynamic stability. Code and data are available at https://github.com/aklipf/GemsNet.","doi":"10.24963/ijcai.2023/669","url":"https://ijcai.org/proceedings/2023/669","pdf":"https://ijcai.org/proceedings/2023/0669.pdf","markdown":"https://ijcai.org/proceedings/2023/669.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/669","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":"AI for Good","track":"AI for Good","number":669,"pages":{"first":6031,"last":6039},"keywords":["AI for Good: Machine Learning","AI for Good: Multidisciplinary Topics and Applications"],"videos":[],"references":[{"position":1,"raw":"[Castelli et al., 2012a] Ivano E Castelli, David D Landis, Kristian S Thygesen, Søren Dahl, Ib Chorkendorff, Thomas F Jaramillo, and Karsten W Jacobsen. New cubic perovskites for one-and two-photon water splitting using the computational materials repository. Energy & Envi- ronmental Science, 5(10):9034-9043, 2012.","title":"New cubic perovskites for one-and two-photon water splitting using the computational materials repository","authors":"Castelli","year":"2012","venue":"Energy & Environmental Science","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Castelli et al., 2012b] Ivano E Castelli, Thomas Olsen, Soumendu Datta, David D Landis, Søren Dahl, Kris- tian S Thygesen, and Karsten W Jacobsen. Computational screening of perovskite metal oxides for optimal solar light capture. Energy & Environmental Science, 5(2):5814- 5819, 2012.","title":"Computational screening of perovskite metal oxides for optimal solar light capture","authors":"Castelli","year":"2012","venue":"Energy & Environmental Science","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2019] Chi Chen, Weike Ye, Yunxing Zuo, Chen Zheng, and Shyue Ping Ong. Graph networks as a univer- sal machine learning framework for molecules and crys- tals. Chemistry of Materials, 31(9):3564-3572, 2019.","title":"Graph networks as a universal machine learning framework for molecules and crystals","authors":"Chen","year":"2019","venue":"Chemistry of Materials","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheon et al., 2020] Gowoon Cheon, Lusann Yang, Kevin McCloskey, Evan J. Reed, and Ekin D. Cubuk. Crystal structure search with random relaxations using graph net- works. arXiv preprint arXiv:2012.02920, 2020.","title":"Crystal structure search with random relaxations using graph networks","authors":"Cheon","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Choudhary and DeCost, 2021] Kamal Choudhary and Brian DeCost. Atomistic line graph neural network for improved materials property predictions. npj Computa- tional Materials, 7(1):185, Nov 2021.","title":"Atomistic line graph neural network for improved materials property predictions","authors":"Kamal Choudhary, Brian Decost","year":"2021","venue":"npj Computational Materials","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Court et al., 2020] Callum J. Court, Batuhan Yildirim, Apoorv Jain, and Jacqueline M. Cole. 3-d inorganic crys- tal structure generation and property prediction via repre- sentation learning. Journal of Chemical Information and Modeling, 60(10):4518-4535, 2020. PMID: 32866381.","title":"Cole. 3-d inorganic crystal structure generation and property prediction via representation learning","authors":"J Callum, Batuhan Court, Apoorv Yildirim, Jacqueline M Jain","year":"2020","venue":"Journal of Chemical Information and Modeling","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ekström Kelvinius et al., 2022] Filip Ekström Kelvinius, Rickard Armiento, and Fredrik Lindsten. Graph-based machine learning beyond stable materials and relaxed crystal structures. Phys. Rev. Materials, 6:033801, Mar 2022.","title":"Graph-based machine learning beyond stable materials and relaxed crystal structures","authors":"Ekström Kelvinius","year":"2022","venue":"Phys. Rev. Materials","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gasteiger et al., 2020a] Johannes Gasteiger, Shankari Giri, Johannes T. Margraf, and Stephan Günnemann. Fast and uncertainty-aware directional message passing for non-equilibrium molecules. In Machine Learning for Molecules Workshop, NeurIPS, 2020.","title":"Fast and uncertainty-aware directional message passing for non-equilibrium molecules","authors":"Gasteiger","year":"2020","venue":"Machine Learning for Molecules Workshop","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gasteiger et al., 2020b] Johannes Gasteiger, Janek Groß, and Stephan Günnemann. Directional message passing for molecular graphs. In International Conference on Learn- ing Representations (ICLR), 2020.","title":"Directional message passing for molecular graphs","authors":"Gasteiger","year":"2020","venue":"International Conference on Learning Representations (ICLR)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gibson et al., 2022] Jason Gibson, Ajinkya Hire, and Richard G. Hennig. Data-augmentation for graph neu- ral network learning of the relaxed energies of unrelaxed structures. npj Computational Materials, 8(1):211, Sep 2022.","title":"Data-augmentation for graph neural network learning of the relaxed energies of unrelaxed structures","authors":"Gibson","year":"2022","venue":"npj Computational Materials","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jain et al., 2013] Anubhav Jain, Shyue Ping Ong, Geoffroy Hautier, Wei Chen, William Davidson Richards, Stephen Dacek, Shreyas Cholia, Dan Gunter, David Skinner, Ger- brand Ceder, et al. Commentary: The materials project: A materials genome approach to accelerating materials inno- vation. APL materials, 1(1):011002, 2013.","title":"Commentary: The materials project: A materials genome approach to accelerating materials innovation","authors":"Anubhav Jain, Ping Shyue, Geoffroy Ong, Wei Hautier, William Davidson Chen, Stephen Richards, Shreyas Dacek, Dan Cholia, David Gunter, Gerbrand Skinner, Ceder","year":"2013","venue":"APL materials","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jørgensen et al., 2018] Peter Bjørn Jørgensen, Karsten Wedel Jacobsen, and Mikkel N. Schmidt. Neural message passing with edge updates for predicting properties of molecules and materials. arXiv preprint arXiv:1806.03146, 2018.","title":"Neural message passing with edge updates for predicting properties of molecules and materials","authors":"Jørgensen","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kim et al., 2020a] Baekjun Kim, Sangwon Lee, and Jihan Kim. Inverse design of porous materials using artificial neural networks. Science Advances, 6(1):eaax9324, 2020.","title":"Inverse design of porous materials using artificial neural networks","authors":"Kim","year":"2020","venue":"Science Advances","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kim et al., 2020b] Sungwon Kim, Juhwan Noh, Geun Ho Gu, Alan Aspuru-Guzik, and Yousung Jung. Genera- tive adversarial networks for crystal structure prediction. ACS Central Science, 6(8):1412-1420, 2020. PMID: 32875082.","title":"Generative adversarial networks for crystal structure prediction","authors":"Kim","year":"2020","venue":"ACS Central Science","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Klicpera et al., 2021] Johannes Klicpera, Florian Becker, and Stephan Günnemann. Gemnet: Universal directional graph neural networks for molecules. In A. Beygelz- imer, Y. Dauphin, P. Liang, and J. Wortman Vaughan, edi- tors, Advances in Neural Information Processing Systems, 2021.","title":"Gemnet: Universal directional graph neural networks for molecules","authors":"Klicpera","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Klipfel et al., 2023] Astrid Klipfel, Olivier Peltre, Najwa Harrati, Yaël Fregier, Adlane Sayede, and Zied Bouraoui. Equivariant message passing neural network for crystal material discovery. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023. AAAI Press, 2023.","title":"Equivariant message passing neural network for crystal material discovery","authors":"Klipfel","year":"2023","venue":"Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Long et al., 2021] Teng Long, Nuno M. Fortunato, Ingo Opahle, Yixuan Zhang, Ilias Samathrakis, Chen Shen, Oliver Gutfleisch, and Hongbin Zhang. Constrained crys- tals deep convolutional generative adversarial network for the inverse design of crystal structures. npj Computational Materials, 7(1):66, May 2021.","title":"Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures","authors":"Teng Long, M Nuno, Ingo Fortunato, Yixuan Opahle, Ilias Zhang, Chen Samathrakis, Oliver Shen, Hongbin Gutfleisch, Zhang","year":"2021","venue":"npj Computational Materials","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Noh et al., 2019] Juhwan Noh, Jaehoon Kim, Helge S. Stein, Benjamin Sanchez-Lengeling, John M. Gregoire, Alan Aspuru-Guzik, and Yousung Jung. Inverse design of solid-state materials via a continuous representation. Mat- ter, 1(5):1370-1384, 2019.","title":"Inverse design of solid-state materials via a continuous representation","authors":"Noh","year":"2019","venue":"Matter","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Nouira et al., 2018] Asma Nouira, Jean-Claude Crivello, and Nataliya Sokolovska. Crystalgan: Learning to dis- cover crystallographic structures with generative adversar- ial networks. CoRR, abs/1810.11203, 2018.","title":"Crystalgan: Learning to discover crystallographic structures with generative adversarial networks","authors":"Asma Nouira, Jean-Claude Crivello, Nataliya Sokolovska","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pickard and Needs, 2011] Chris J Pickard and R J Needs. Ab initio random structure searching. Journal of Physics: Condensed Matter, 23(5):053201, jan 2011.","title":"Ab initio random structure searching","authors":"J Chris, R J Pickard, Needs","year":"2011","venue":"Journal of Physics: Condensed Matter","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pickard, 2020] Chris J. Pickard. Airss data for carbon at 10gpa and the c+n+h+o system at 1gpa. Materials Cloud, 2020.","title":"Airss data for carbon at 10gpa and the c+n+h+o system at 1gpa","authors":"Chris J Pickard","year":"2020","venue":"Materials Cloud","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Satorras et al., 2021] Víctor Garcia Satorras, Emiel Hooge- boom, and Max Welling. E(n) equivariant graph neural networks. In Marina Meila and Tong Zhang, editors, Pro- ceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learn- ing Research, pages 9323-9332. PMLR, 18-24 Jul 2021.","title":"E(n) equivariant graph neural networks","authors":"Garcia Víctor, Emiel Satorras, Max Hoogeboom, Welling","year":"2021","venue":"Proceedings of the 38th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Schütt et al., 2017] Kristof Schütt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexan- dre Tkatchenko, and Klaus-Robert Müller. Schnet: A continuous-filter convolutional neural network for model- ing quantum interactions. In NIPS, pages 992-1002, 2017.","title":"Schnet: A continuous-filter convolutional neural network for modeling quantum interactions","authors":"Schütt","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xie et al., 2022] Tian Xie, Xiang Fu, Octavian-Eugen Ganea, Regina Barzilay, and Tommi S. Jaakkola. Crys- tal diffusion variational autoencoder for periodic mate- rial generation. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, 2022.","title":"Crystal diffusion variational autoencoder for periodic material generation","authors":"Tian Xie, Xiang Fu, Octavian-Eugen Ganea, Regina Barzilay, Tommi S Jaakkola","year":"2022","venue":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}