{"type":"ScholarlyArticle","title":"HypBO: Accelerating Black-Box Scientific Experiments Using Experts’ Hypotheses","authors":[{"name":"Abdoulatif Cissé","slug":"abdoulatif-cisse","given":"Abdoulatif","family":"Cissé","affiliation":"Department of Chemistry , University of Liverpool , England , UK; Leverhulme Research Centre for Functional Materials Design , University of Liverpool , England , UK"},{"name":"Xenophon Evangelopoulos","slug":"xenophon-evangelopoulos","given":"Xenophon","family":"Evangelopoulos","affiliation":"Department of Chemistry , University of Liverpool , England , UK; Leverhulme Research Centre for Functional Materials Design , University of Liverpool , England , UK"},{"name":"Sam Carruthers","slug":"sam-carruthers","given":"Sam","family":"Carruthers","affiliation":"Department of Chemistry , University of Liverpool , England , UK; Leverhulme Research Centre for Functional Materials Design , University of Liverpool , England , UK"},{"name":"Vladimir V. Gusev","slug":"vladimir-v-gusev","given":"Vladimir V.","family":"Gusev","affiliation":"Department of Computer Science , University of Liverpool , England , UK"},{"name":"Andrew I. Cooper","slug":"andrew-i-cooper","given":"Andrew I.","family":"Cooper","affiliation":"Department of Chemistry , University of Liverpool , England , UK; Leverhulme Research Centre for Functional Materials Design , University of Liverpool , England , UK"}],"abstract":"Robotics and automation offer massive acceleration for solving intractable, multivariate scientific problems such as materials discovery, but the available search spaces can be dauntingly large. Bayesian optimization has emerged as a popular sample-efficient optimization engine, thriving in tasks where no analytic form of the target function/property is known. Here, we exploit expert human knowledge in the form of hypotheses to direct Bayesian searches more quickly to promising regions of chemical space. Previous methods have used underlying distributions derived from existing experimental measurements, which is unfeasible for new, unexplored scientific tasks. Also, such distributions cannot capture intricate hypotheses. Our proposed method uses expert human hypotheses to generate improved seed samples. Unpromising seeds are automatically discounted, while promising seeds are used to augment the surrogate model data, thus achieving better-informed sampling. This process continues in a global versus local search fashion, organized in a bilevel optimization framework. We validate the performance of our method on a range of synthetic functions and demonstrate its practical utility on a real chemical design task where the use of expert hypotheses accelerates the search performance significantly.","doi":"10.24963/ijcai.2024/429","url":"https://ijcai.org/proceedings/2024/429","pdf":"https://ijcai.org/proceedings/2024/0429.pdf","markdown":"https://ijcai.org/proceedings/2024/429.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/429","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":429,"pages":{"first":3881,"last":3889},"keywords":["Machine Learning: ML: Bayesian learning","Knowledge Representation and Reasoning: KRR: Learning and reasoning","Machine Learning: ML: Optimization","Humans and AI: HAI: Human-AI collaboration"],"videos":[],"references":[{"position":1,"raw":"[Anjanapura Venkatesh et al., 2022] Arun Kumar Anjana- pura Venkatesh, Santu Rana, Alistair Shilton, and Svetha Venkatesh. Human-ai collaborative bayesian optimisa- tion. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Informa- tion Processing Systems, volume 35, pages 16233-16245.","title":"Human-ai collaborative bayesian optimisation","authors":"Arun Kumar, Anjanapura Venkatesh, Santu Rana, Alistair Shilton, Svetha Venkatesh","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Curran Associates, Inc., 2022.","title":null,"authors":"Curran Associates, Inc","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bonferroni, 1936] Carlo E. Bonferroni. Teoria statistica delle classi e calcolo delle probabilità. Pubblicazioni del R. Istituto superiore di scienze economiche e commerciali di Firenze. Seeber, 1936.","title":"Teoria statistica delle classi e calcolo delle probabilità. Pubblicazioni del R. Istituto superiore di scienze economiche e commerciali di Firenze","authors":"Carlo E Bonferroni","year":"1936","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Burger et al., 2020] Benjamin Burger, Phillip M. Maffet- tone, Vladimir V. Gusev, Catherine M. Aitchison, Yang Bai, Xiao yan Wang, Xiaobo Li, Ben M. Alston, Buyin Li, Rob Clowes, Nicola Rankin, Brandon Harris, Reiner Se- bastian Sprick, and Andrew I. Cooper. A mobile robotic chemist. Nature, 583:237-241, 2020.","title":"Cooper. A mobile robotic chemist","authors":"Benjamin Burger, Phillip M Maffettone, Vladimir V Gusev, Catherine M Aitchison, Yang Bai, Xiaobo Xiao Yan Wang, Ben M Li, Buyin Alston, Rob Li, Nicola Clowes, Brandon Rankin, Reiner Harris, Andrew I Sebastian Sprick","year":"2020","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Diouane et al., 2021] Youssef Diouane, Victor Picheny, Rodolophe Le Riche, and Alexandre Scotto Di Perrotolo. Trego: a trust-region framework for efficient global opti- mization. Journal of Global Optimization, 86:1-23, 2021.","title":"Trego: a trust-region framework for efficient global optimization","authors":"Youssef Diouane, Victor Picheny, Rodolophe Le Riche, Alexandre Scotto, Di Perrotolo","year":"2021","venue":"Journal of Global Optimization","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Eriksson et al., 2019] David Eriksson, Michael Pearce, Ja- cob Gardner, Ryan D Turner, and Matthias Poloczek. Scal- able global optimization via local bayesian optimization. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché- Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 32.","title":"Scalable global optimization via local bayesian optimization","authors":"David Eriksson, Michael Pearce, Jacob Gardner, Ryan D Turner, Matthias Poloczek","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hernández-Lobato et al., 2015] José Miguel Hernández- Lobato, Michael Gelbart, Matthew Hoffman, Ryan Adams, and Zoubin Ghahramani. Predictive entropy search for bayesian optimization with unknown con- straints. In International Conference on Machine Learn- ing, pages 1699-1707. PMLR, 2015.","title":"Predictive entropy search for bayesian optimization with unknown constraints","authors":"Hernández-Lobato","year":"2015","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hickman et al., 2023] Riley J. Hickman, Jurgis Ruža, Her- mann Tribukait, Loïc M. Roch, and Alberto García- Durán. Equipping data-driven experiment planning for self-driving laboratories with semantic memory: case studies of transfer learning in chemical reaction optimiza- tion. Reaction Chemistry & Engineering, 2023.","title":"Equipping data-driven experiment planning for self-driving laboratories with semantic memory: case studies of transfer learning in chemical reaction optimization","authors":"Riley J Hickman, Jurgis Ruža, Hermann Tribukait, Loïc M Roch, Alberto García-Durán","year":"2023","venue":"Reaction Chemistry & Engineering","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2022] Daolang Huang, Louis Filstroff, Petrus Mikkola, Runkai Zheng, and Samuel Kaski. Bayesian op- timization augmented with actively elicited expert knowl- edge. arXiv:2208.08742, 2022.","title":"Bayesian optimization augmented with actively elicited expert knowledge","authors":"Huang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hvarfner et al., 2022] Carl Hvarfner, Danny Stoll, Artur Souza, Luigi Nardi, Marius Lindauer, and Frank Hutter. πBO: Augmenting acquisition functions with user beliefs for bayesian optimization. In 10th International Confer- ence on Learning Representations, ICLR'22, pages 1-30, April 2022.","title":"πBO: Augmenting acquisition functions with user beliefs for bayesian optimization","authors":"Carl Hvarfner, Danny Stoll, Artur Souza, Luigi Nardi, Marius Lindauer, Frank Hutter","year":"2022","venue":"10th International Conference on Learning Representations, ICLR'22","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hvarfner et al., 2024] Carl Hvarfner, Frank Hutter, and Luigi Nardi. A general framework for user-guided bayesian optimization. In The Twelfth International Con- ference on Learning Representations, 2024.","title":"A general framework for user-guided bayesian optimization","authors":"Carl Hvarfner, Frank Hutter, Luigi Nardi","year":"2024","venue":"The Twelfth International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Häse et al., 2021] Florian Häse, Matteo Aldeghi, Riley J. Hickman, Loïc M. Roch, and Alán Aspuru-Guzik. Gryf- fin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge. Applied Physics Reviews, 8(3):031406, 07 2021.","title":"Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge","authors":"Florian Häse, Matteo Aldeghi, Riley J Hickman, Loïc M Roch, Alán Aspuru-Guzik","year":null,"venue":"Applied Physics Reviews","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jones et al., 1998] Donald R. Jones, Matthias Schonlau, and William J. Welch. Efficient global optimization of expen- sive black-box functions. Journal of Global Optimization, 13(4):455-492, 1998.","title":"Efficient global optimization of expensive black-box functions","authors":"Donald R Jones, Matthias Schonlau, William J Welch","year":"1998","venue":"Journal of Global Optimization","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Köppe et al., 2010] Matthias Köppe, Maurice Queyranne, and Christopher Thomas Ryan. Parametric integer programming algorithm for bilevel mixed integer pro- grams. Journal of Optimization Theory and Applications, 146(1):137-150, 2010.","title":"Parametric integer programming algorithm for bilevel mixed integer programs","authors":"Matthias Köppe, Maurice Queyranne, Christopher Thomas, Ryan","year":"2010","venue":"Journal of Optimization Theory and Applications","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2020] Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Antonio Robles-Kelly, and Svetha Venkatesh. Incorporating expert prior knowledge into experimental design via posterior sampling. arxiv:2002.11256, 2020.","title":"Incorporating expert prior knowledge into experimental design via posterior sampling","authors":"Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Antonio Robles-Kelly, Svetha Venkatesh","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Martinelli et al., 2023] Julien Martinelli, Yasmine Nahal, Duong Lê, Ola Engkvist, and Samuel Kaski. Leveraging expert feedback to align proxy and ground truth rewards in goal-oriented molecular generation. In NeurIPS 2023 Workshop on New Frontiers of AI for Drug Discovery and Development, 2023.","title":"Leveraging expert feedback to align proxy and ground truth rewards in goal-oriented molecular generation","authors":"Julien Martinelli, Yasmine Nahal, Duong Lê, Ola Engkvist, Samuel Kaski","year":"2023","venue":"NeurIPS 2023 Workshop on New Frontiers of AI for Drug Discovery and Development","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Morishita and Kaneko, 2023] Toshiharu Morishita and Hi- romasa Kaneko. Initial sample selection in bayesian opti- mization for combinatorial optimization of chemical com- pounds. ACS Omega, 8(2):2001-2009, 2023.","title":"Initial sample selection in bayesian optimization for combinatorial optimization of chemical compounds","authors":"Kaneko Morishita","year":"2023","venue":"ACS Omega","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nguyen et al., 2024] Quoc Phong Nguyen, Wan Theng Ruth Chew, Le Song, Bryan Kian Hsiang Low, and Patrick Jaillet. Optimistic bayesian optimization with unknown constraints. In The Twelfth International Conference on Learning Representations, 2024.","title":"Optimistic bayesian optimization with unknown constraints","authors":"Phong Quoc, Wan Nguyen, Ruth Theng, Le Chew, Bryan Kian Hsiang Song, Patrick Low, Jaillet","year":"2024","venue":"The Twelfth International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Niu et al., 2020] Shuteng Niu, Yongxin Liu, Jian Wang, and Houbing Song. A decade survey of transfer learn- ing (2010-2020). IEEE Transactions on Artificial Intelli- gence, 1(2):151-166, 2020.","title":"A decade survey of transfer learning (2010-2020)","authors":"Niu","year":"2020","venue":"IEEE Transactions on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ramachandran et al., 2020] Anil Ramachandran, Sunil Gupta, Santu Rana, Cheng Li, and Svetha Venkatesh. Incorporating expert prior in bayesian optimisation via space warping. Knowledge-Based Systems, 195:105663, 2020.","title":"Incorporating expert prior in bayesian optimisation via space warping","authors":"Anil Ramachandran, Sunil Gupta, Santu Rana, Cheng Li, Svetha Venkatesh","year":"2020","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rasmussen and Williams, 2006] Carl Edward Rasmussen and Christopher K. I. Williams. Gaussian processes for machine learning. Adaptive computation and machine learning. MIT Press, 2006.","title":"Gaussian processes for machine learning. Adaptive computation and machine learning","authors":"Carl Edward Rasmussen, Christopher K I Williams","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rey and Neuhäuser, 2011] Denise Rey and Markus Neuhäuser. Wilcoxon-signed-rank test, pages 1658-1659. Springer Berlin Heidelberg, Berlin, Heidelberg, 2011.","title":"Wilcoxon-signed-rank test","authors":"Denise Rey, Markus Neuhäuser","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Shahriari et al., 2016] Bobak Shahriari, Kevin Swersky, Ziyu Wang, Ryan P. Adams, and Nando de Freitas. Taking the human out of the loop: A review of bayesian optimiza- tion. Proceedings of the IEEE, 104(1), 2016.","title":"Taking the human out of the loop: A review of bayesian optimization","authors":"Bobak Shahriari, Kevin Swersky, Ziyu Wang, Ryan P Adams, Nando De Freitas","year":"2016","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Siemenn et al., 2023] Alexander E. Siemenn, Zekun Ren, Qianxiao Li, and Tonio Buonassisi. Fast bayesian opti- mization of needle-in-a-haystack problems using zooming memory-based initialization (zombi). npj Computational Materials, 9(1), May 2023.","title":"Fast bayesian optimization of needle-in-a-haystack problems using zooming memory-based initialization (zombi)","authors":"Alexander E Siemenn, Zekun Ren, Qianxiao Li, Tonio Buonassisi","year":"2023","venue":"npj Computational Materials","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Souza et al., 2021] Artur Souza, Luigi Nardi, Leonardo B. Oliveira, Kunle Olukotun, Marius Lindauer, and Frank Hutter. Bayesian optimization with a prior for the op- timum. In Nuria Oliver, Fernando Pérez-Cruz, Stefan Kramer, Jesse Read, and Jose A. Lozano, editors, Ma- chine Learning and Knowledge Discovery in Databases. Research Track, pages 265-296, Cham, 2021. Springer In- ternational Publishing.","title":"Bayesian optimization with a prior for the optimum","authors":"Artur Souza, Luigi Nardi, Leonardo B Oliveira, Kunle Olukotun, Marius Lindauer, Frank Hutter","year":"2021","venue":"Machine Learning and Knowledge Discovery in Databases. Research Track","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sundin et al., 2018] Iiris Sundin, Tomi Peltola, Luana Mi- callef, Homayun Afrabandpey, Marta Soare, Muntasir Ma- mun Majumder, Pedram Daee, Chen He, Baris Serim, Aki Havulinna, Caroline Heckman, Giulio Jacucci, Pekka Marttinen, and Samuel Kaski. Improving genomics-based predictions for precision medicine through active elicita- tion of expert knowledge. Bioinformatics (Oxford, Eng- land), 34:i395-i403, 07 2018.","title":"Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge","authors":"Iiris Sundin, Tomi Peltola, Luana Micallef, Homayun Afrabandpey, Marta Soare, Mamun Muntasir, Pedram Majumder, Chen Daee, Baris He, Aki Serim, Caroline Havulinna, Giulio Heckman, Pekka Jacucci, Samuel Marttinen, Kaski","year":"2018","venue":"Bioinformatics (Oxford, England)","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Tay et al., 2023] Sebastian Tay, Chuan Sheng Foo, Daisuke Urano, Richalynn Leong, and Bryan Kian Hsiang Low. Bayesian optimization with cost-varying variable sub- sets. In A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural In- formation Processing Systems, volume 36, pages 3008- 3031.","title":"Bayesian optimization with cost-varying variable subsets","authors":"Sebastian Tay, Chuan Sheng Foo, Daisuke Urano, Richalynn Leong, Bryan Kian, Hsiang Low","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"Curran Associates, Inc., 2023.","title":null,"authors":"Curran Associates, Inc","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Theckel Joy et al., 2019] Tinu Theckel Joy, Santu Rana, Sunil Gupta, and Svetha Venkatesh. A flexible transfer learning framework for bayesian optimization with con- vergence guarantee. Expert Systems with Applications, 115:656-672, 2019.","title":"A flexible transfer learning framework for bayesian optimization with convergence guarantee","authors":"Tinu Theckel, Joy, Santu Rana, Sunil Gupta, Svetha Venkatesh","year":"2019","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Vermorel and Mohri, 2005] Joannès Vermorel and Mehryar Mohri. Multi-armed bandit algorithms and empirical eval- uation. In Proceedings of the 16th European Conference on Machine Learning, ECML'05, page 437-448, Berlin, Heidelberg, 2005. Springer-Verlag.","title":"Joannès Vermorel and Mehryar Mohri. Multi-armed bandit algorithms and empirical evaluation","authors":"Mohri Vermorel","year":"2005","venue":"Proceedings of the 16th European Conference on Machine Learning, ECML'05","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wang et al., 2019] Zheng Wang, Can Li, and Kazunari Domen. Recent developments in heterogeneous photocat- alysts for solar-driven overall water splitting. Chemical Society Reviews, 48:2109-2125, 2019.","title":"Recent developments in heterogeneous photocatalysts for solar-driven overall water splitting","authors":"Zheng Wang, Can Li, Kazunari Domen","year":"2019","venue":"Chemical Society Reviews","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Wang et al., 2020] Linnan Wang, Rodrigo Fonseca, and Yuandong Tian. Learning search space partition for black-box optimization using monte carlo tree search. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Process- ing Systems, volume 33, pages 19511-19522.","title":"Learning search space partition for black-box optimization using monte carlo tree search","authors":"Linnan Wang, Rodrigo Fonseca, Yuandong Tian","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Ziatdinov et al., 2022] Maxim A. Ziatdinov, Yongtao Liu, Anna N. Morozovska, Eugene A. Eliseev, Xiaohang Zhang, Ichiro Takeuchi, and Sergei V. Kalinin. Hypothesis learning in automated experiment: application to combi- natorial materials libraries. Advanced Materials, 34(20), April 2022.","title":"Hypothesis learning in automated experiment: application to combinatorial materials libraries","authors":"Ziatdinov","year":"2022","venue":"Advanced Materials","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}