{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T12:55:35Z","timestamp":1753880135978,"version":"3.41.2"},"reference-count":40,"publisher":"ASME International","issue":"5","license":[{"start":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T00:00:00Z","timestamp":1706486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/100008582","name":"McGill University","doi-asserted-by":"publisher","award":["00157"],"award-info":[{"award-number":["00157"]}],"id":[{"id":"10.13039\/100008582","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","award":["IT13369"],"award-info":[{"award-number":["IT13369"]}],"id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The design dataset is the backbone of data-driven design. Ideally, the dataset should be fairly distributed in both shape and property spaces to efficiently explore the underlying relationship. However, the classical experimental design focuses on shape diversity and thus yields biased exploration in the property space. Recently developed methods either conduct subset selection from a large dataset or employ assumptions with severe limitations. In this paper, fairness- and uncertainty-aware data generation (FairGen) is proposed to actively detect and generate missing properties starting from a small dataset. At each iteration, its coverage module computes the data coverage to guide the selection of the target properties. The uncertainty module ensures that the generative model can make certain and thus accurate shape predictions. Integrating the two modules, Bayesian optimization determines the target properties, which are thereafter fed into the generative model to predict the associated shapes. The new designs, whose properties are analyzed by simulation, are added to the design dataset. This constructs an active learning mechanism that iteratively samples new data to improve data representativeness and machine learning model performance. An S-slot design dataset case study was implemented to demonstrate the efficiency of FairGen in auxetic structural design. Compared with grid and randomized sampling, FairGen increased the coverage score at twice the speed and significantly expanded the sampled region in the property space. As a result, the generative models trained with FairGen-generated datasets showed consistent and significant reductions in mean absolute errors.<\/jats:p>","DOI":"10.1115\/1.4064408","type":"journal-article","created":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T11:14:11Z","timestamp":1704366851000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":1,"title":["Fairness- and Uncertainty-Aware Data Generation for Data-Driven Design Based on Active Learning"],"prefix":"10.1115","volume":"24","author":[{"given":"Jiarui","family":"Xie","sequence":"first","affiliation":[{"name":"McGill University Department of Mechanical Engineering, , 845 Sherbrooke St W, Montreal, QC H3A 0G4 , Canada"}]},{"given":"Chonghui","family":"Zhang","sequence":"additional","affiliation":[{"name":"McGill University Department of Mechanical Engineering, , 845 Sherbrooke St W, Montreal, QC H3A 0G4 , Canada"}]},{"given":"Lijun","family":"Sun","sequence":"additional","affiliation":[{"name":"McGill University Department of Civil Engineering, , 845 Sherbrooke St W, Montreal, QC H3A 0G4 , Canada"}]},{"given":"Yaoyao Fiona","family":"Zhao","sequence":"additional","affiliation":[{"name":"McGill University Department of Mechanical Engineering, , 845 Sherbrooke St W, Montreal, QC H3A 0G4 , Canada"}]}],"member":"33","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"issue":"5","key":"2024041814391815100_CIT0001","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/s00466-018-1539-z","article-title":"Data-Driven Multi-scale Multi-physics Models to Derive Process\u2013Structure\u2013Property Relationships for Additive Manufacturing","volume":"61","author":"Yan","year":"2018","journal-title":"Comput. Mech."},{"key":"2024041814391815100_CIT0002","first-page":"170","article-title":"On Artificial Intelligence for Simulation and Design Space Exploration in Gas Turbine Design","author":"Pilarski","year":"2019"},{"issue":"3","key":"2024041814391815100_CIT0003","doi-asserted-by":"publisher","first-page":"031703","DOI":"10.1115\/1.4048626","article-title":"Padgan: Learning to Generate High-Quality Novel Designs","volume":"143","author":"Chen","year":"2021","journal-title":"ASME J. Mech. Des."},{"key":"2024041814391815100_CIT0004","doi-asserted-by":"publisher","first-page":"103225","DOI":"10.1016\/j.cad.2022.103225","article-title":"Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs","volume":"146","author":"Jang","year":"2022","journal-title":"Comput. Aided Des."},{"issue":"4","key":"2024041814391815100_CIT0005","doi-asserted-by":"publisher","first-page":"041004","DOI":"10.1115\/1.4056297","article-title":"Reinforcement Learning for Efficient Design Space Exploration With Variable Fidelity Analysis Models","volume":"23","author":"Agrawal","year":"2023","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"6","key":"2024041814391815100_CIT0006","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1007\/s00158-020-02523-5","article-title":"Data-Driven Metamaterial Design With Laplace-Beltrami Spectrum as \u2018Shape-DNA\u2019","volume":"61","author":"Wang","year":"2020","journal-title":"Struct. Multidiscipl. Optim."},{"issue":"2","key":"2024041814391815100_CIT0007","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3390\/designs4020010","article-title":"Generative Design by Using Exploration Approaches of Reinforcement Learning in Density-Based Structural Topology Optimization","volume":"4","author":"Sun","year":"2020","journal-title":"Designs"},{"issue":"11","key":"2024041814391815100_CIT0008","doi-asserted-by":"publisher","first-page":"111405","DOI":"10.1115\/1.4044229","article-title":"Deep Generative Design: Integration of Topology Optimization and Generative Models","volume":"141","author":"Oh","year":"2019","journal-title":"ASME J. Mech. Des."},{"issue":"1","key":"2024041814391815100_CIT0009","doi-asserted-by":"publisher","first-page":"011012","DOI":"10.1115\/1.4055924","article-title":"Physics-Constrained Bayesian Neural Network for Bias and Variance Reduction","volume":"23","author":"Malashkhia","year":"2023","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"3","key":"2024041814391815100_CIT0010","doi-asserted-by":"publisher","first-page":"031008","DOI":"10.1115\/1.4055316","article-title":"Multifidelity Physics-Constrained Neural Networks With Minimax Architecture","volume":"23","author":"Liu","year":"2023","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"3","key":"2024041814391815100_CIT0011","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1109\/TR.2022.3200137","article-title":"An Overview of Adaptive-Surrogate-Model-Assisted Methods for Reliability-Based Design Optimization","volume":"72","author":"Ling","year":"2022","journal-title":"IEEE Trans. Reliab."},{"key":"2024041814391815100_CIT0012","doi-asserted-by":"crossref","DOI":"10.1088\/978-0-7503-1218-9","volume-title":"Inverse Modeling","author":"Nakamura","year":"2015"},{"key":"2024041814391815100_CIT0013","first-page":"1","article-title":"A Framework for Understanding Sources of Harm Throughout the Machine Learning Life Cycle","author":"Suresh","year":"2021"},{"key":"2024041814391815100_CIT0014","doi-asserted-by":"crossref","DOI":"10.1115\/DETC2022-87653","article-title":"t-METASET: Task-Aware Generation of Metamaterial Datasets by Diversity-Based Active Learning","author":"Lee","year":"2022"},{"issue":"3","key":"2024041814391815100_CIT0015","doi-asserted-by":"publisher","first-page":"031707","DOI":"10.1115\/1.4048629","article-title":"METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design","volume":"143","author":"Chan","year":"2021","journal-title":"ASME J. Mech. Des."},{"key":"2024041814391815100_CIT0016","first-page":"1","article-title":"Fairness & Friends in the Data Science Era","volume":"38","author":"Catania","year":"2022","journal-title":"AI Soc."},{"issue":"13","key":"2024041814391815100_CIT0017","first-page":"1","article-title":"A Survey on Techniques for Identifying and Resolving Representation Bias in Data","volume":"55","author":"Shahbazi","year":"2022","journal-title":"ACM Comput. Surv."},{"issue":"10","key":"2024041814391815100_CIT0018","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s00158-022-03402-x","article-title":"Adaptive Surrogate Modeling for High-Dimensional Spatio-temporal Output","volume":"65","author":"Kapusuzoglu","year":"2022","journal-title":"Struct. Multidiscipl. Optim."},{"issue":"8","key":"2024041814391815100_CIT0019","doi-asserted-by":"publisher","first-page":"081701","DOI":"10.1115\/1.4053526","article-title":"An Adaptive Dendrite-HDMR Metamodeling Technique for High-Dimensional Problems","volume":"144","author":"Zhang","year":"2022","journal-title":"ASME J. Mech. Des."},{"key":"2024041814391815100_CIT0020","first-page":"1510","article-title":"Deep Neural Network Hardware Deployment Optimization Via Advanced Active Learning","author":"Sun","year":"2021"},{"issue":"5","key":"2024041814391815100_CIT0021","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3398268","article-title":"Multi-fidelity Surrogate-Based Optimization for Electromagnetic Simulation Acceleration","volume":"25","author":"Wang","year":"2020","journal-title":"ACM Trans. Des. Autom. Electron. Syst."},{"key":"2024041814391815100_CIT0022","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1016\/j.actaastro.2022.11.007","article-title":"Design of Double Layer Protective Coatings: Finite Element Modeling and Machine Learning Approximations","volume":"204","author":"Kolesnikov","year":"2023","journal-title":"Acta Astronaut."},{"key":"2024041814391815100_CIT0023","first-page":"6220","article-title":"Gaussian Process Adaptive Sampling Using the Cross-Entropy Method for Environmental Sensing and Monitoring","author":"Tan","year":"2018"},{"key":"2024041814391815100_CIT0024","doi-asserted-by":"crossref","DOI":"10.1115\/DETC2022-91196","article-title":"Hall Effect Sensor Design Optimization With Multi-physics Informed Gaussian Process Modeling","author":"Xu","year":"2022"},{"key":"2024041814391815100_CIT0025","first-page":"1","article-title":"Design of Additively Manufactured Functionally Graded Cellular Structures","author":"Liu","year":"2022"},{"article-title":"Fairness- and Uncertainty-Aware Data Generation for Data-Driven Design","year":"2022","author":"Xie","key":"2024041814391815100_CIT0026"},{"key":"2024041814391815100_CIT0027","first-page":"129","article-title":"Identifying Insufficient Data Coverage for Ordinal Continuous-Valued Attributes","author":"Asudeh","year":"2021"},{"issue":"3","key":"2024041814391815100_CIT0028","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1145\/116873.116880","article-title":"Voronoi Diagrams\u2014A Survey of a Fundamental Geometric Data Structure","volume":"23","author":"Aurenhammer","year":"1991","journal-title":"ACM Comput. Surv."},{"volume-title":"Spatial Tessellations: Concepts and Applications of Voronoi Diagrams","year":"2009","author":"Boots","key":"2024041814391815100_CIT0029"},{"issue":"2\u20133","key":"2024041814391815100_CIT0030","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/S0951-8320(96)00077-4","article-title":"Aleatory and Epistemic Uncertainty in Probability Elicitation With an Example From Hazardous Waste Management","volume":"54","author":"Hora","year":"1996","journal-title":"Reliab. Eng. Syst. Saf."},{"issue":"3","key":"2024041814391815100_CIT0031","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","article-title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","volume":"110","author":"H\u00fcllermeier","year":"2021","journal-title":"Mach. Learn."},{"article-title":"Simple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles","year":"2018","author":"Lakshminarayanan","key":"2024041814391815100_CIT0032"},{"volume-title":"Mixture Density Networks","year":"1994","author":"Bishop","key":"2024041814391815100_CIT0033"},{"key":"2024041814391815100_CIT0034","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.eml.2017.08.002","article-title":"On the Design of Porous Structures With Enhanced Fatigue Life","volume":"16","author":"Javid","year":"2017","journal-title":"Extreme Mech. Lett."},{"key":"2024041814391815100_CIT0035","doi-asserted-by":"publisher","first-page":"106413","DOI":"10.1016\/j.engappai.2023.106413","article-title":"A Hybrid Deep Learning Approach for the Design of 2D Low Porosity Auxetic Metamaterials","volume":"123","author":"Zhang","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"11","key":"2024041814391815100_CIT0036","doi-asserted-by":"publisher","first-page":"1847","DOI":"10.1002\/adem.201600053","article-title":"Three Decades of Auxetics Research\u2014Materials With Negative Poisson's Ratio: A Review","volume":"18","author":"Saxena","year":"2016","journal-title":"Adv. Eng. Mater."},{"issue":"1","key":"2024041814391815100_CIT0037","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1002\/agj2.20048","article-title":"Guiding Soil Sampling Strategies Using Classical and Spatial Statistics: A Review","volume":"112","author":"Lawrence","year":"2020","journal-title":"Agron. J."},{"key":"2024041814391815100_CIT0038","doi-asserted-by":"publisher","first-page":"113159","DOI":"10.1016\/j.enconman.2020.113159","article-title":"Performance Analysis of Two-Stage Thermoelectric Generator Model Based on Latin Hypercube Sampling","volume":"221","author":"Zhang","year":"2020","journal-title":"Energy Convers. Manage."},{"key":"2024041814391815100_CIT0039","first-page":"251","article-title":"Voronoi Diagrams and Arrangements","author":"Edelsbrunner","year":"1985"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"2024041814391815100_CIT0040"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/5\/051004\/7329348\/jcise_24_5_051004.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/5\/051004\/7329348\/jcise_24_5_051004.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T14:39:26Z","timestamp":1713451166000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/5\/051004\/1193818\/Fairness-and-Uncertainty-Aware-Data-Generation-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,29]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4064408","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"type":"print","value":"1530-9827"},{"type":"electronic","value":"1944-7078"}],"subject":[],"published":{"date-parts":[[2024,1,29]]},"article-number":"051004"}}