{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T15:35:39Z","timestamp":1764084939031,"version":"3.37.3"},"reference-count":42,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006133","name":"Advanced Research Projects Agency - Energy","doi-asserted-by":"crossref","award":["DE-AR0001435"],"award-info":[{"award-number":["DE-AR0001435"]}],"id":[{"id":"10.13039\/100006133","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The design of novel High Entropy Alloys for use in high-temperature applications is an area of active interest due to their potential to provide exceptional properties compared to conventional alloys. Since the increased popularity of machine learning, an important cog in the design process has been training surrogate models on alloy properties. However, these Single-Task models are trained on individual mechanical properties and do not take advantage of the relatedness between properties. Multi-Task models can capture the interdependencies between tasks, leading to potentially more accurate predictions for all tasks. In this paper, we investigate if Multi-Task models can show improvement over Single-Task models when used for predicting the mechanical properties of these alloys. To ensure fair evaluation between the models, we apply <jats:italic>L<\/jats:italic>\n                  <jats:sub>0<\/jats:sub> regularization and skip connections to the models, which allows them to adjust the number of model parameters and depth for optimal performance. We find that the Multi-Task models can leverage task relationships to perform better than Single-Task models, especially for high amounts of missing data in the tasks. Furthermore, adding simple auxiliary targets can boost Multi-Task performance even further despite not being effective as input descriptors to single-task models themselves. We anticipate that the proposed strategies can achieve more accurate predictions and consequently enable better design capabilities for such data-constrained domains without incurring much additional computational cost.<\/jats:p>","DOI":"10.1088\/2632-2153\/adb53c","type":"journal-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T22:57:02Z","timestamp":1739401022000},"page":"015046","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Overcoming sparse datasets with multi-task learning as applied to high entropy alloys"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9427-4499","authenticated-orcid":true,"given":"Arindam","family":"Debnath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7256-2123","authenticated-orcid":true,"given":"Wesley F","family":"Reinhart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"mlstadb53cbib1","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1186\/s10033-022-00814-0","article-title":"Research progress of refractory high entropy alloys: a review","volume":"35","author":"Xie","year":"2022","journal-title":"Chin. J. Mech. Eng."},{"key":"mlstadb53cbib2","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.msea.2003.10.257","article-title":"Microstructural development in equiatomic multicomponent alloys","volume":"375-377","author":"Cantor","year":"2004","journal-title":"Mater. Sci. Eng. A"},{"key":"mlstadb53cbib3","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1002\/adem.200300567","article-title":"Nanostructured high-entropy alloys with multiple principal elements: novel alloy design concepts and outcomes","volume":"6","author":"Wei Yeh","year":"2004","journal-title":"Adv. Eng. Mater."},{"key":"mlstadb53cbib4","doi-asserted-by":"publisher","first-page":"3092","DOI":"10.1557\/jmr.2018.153","article-title":"Development and exploration of refractory high entropy alloys-a review","volume":"33","author":"Senkov","year":"2018","journal-title":"J. Mater. Res."},{"key":"mlstadb53cbib5","doi-asserted-by":"publisher","first-page":"7213","DOI":"10.3390\/ma14237213","article-title":"Machine learning-based strength prediction for refractory high-entropy alloys of the Al-Cr-Nb-Ti-V-Zr system","volume":"14","author":"Klimenko","year":"2021","journal-title":"Materials"},{"key":"mlstadb53cbib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jallcom.2021.161187","article-title":"Investigation of phase-transformation path in TiZrHf(VNbTa)x refractory high-entropy alloys and its effect on mechanical property","volume":"886","author":"Jung","year":"2021","journal-title":"J. Alloys Compd."},{"article-title":"Data-driven materials discovery and synthesis using machine learning methods","year":"2022","author":"Baird","key":"mlstadb53cbib7"},{"key":"mlstadb53cbib8","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1038\/s41524-022-00945-x","article-title":"Element-wise representations with ecnet for material property prediction and applications in high-entropy alloys","volume":"8","author":"Wang","year":"2022","journal-title":"npj Comput. Mater."},{"article-title":"Do graph neural networks work for high entropy alloys?","year":"2024","author":"Zhang","key":"mlstadb53cbib9"},{"key":"mlstadb53cbib10","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.actamat.2019.03.010","article-title":"Machine learning assisted design of high entropy alloys with desired property","volume":"170","author":"Wen","year":"2019","journal-title":"Acta Mater."},{"key":"mlstadb53cbib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2021.117431","article-title":"A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness","volume":"222","author":"Yang","year":"2022","journal-title":"Acta Mater."},{"key":"mlstadb53cbib12","doi-asserted-by":"publisher","DOI":"10.1016\/j.mtcomm.2020.101871","article-title":"Yield strength prediction of high-entropy alloys using machine learning","volume":"26","author":"Bhandari","year":"2021","journal-title":"Mater. Today Commun."},{"key":"mlstadb53cbib13","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41524-023-01010-x","article-title":"A neural network model for high entropy alloy design","volume":"9","author":"Wang","year":"2023","journal-title":"npj Comput. Mater."},{"key":"mlstadb53cbib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2022.118133","article-title":"Multi-objective materials bayesian optimization with active learning of design constraints: design of ductile refractory multi-principal-element alloys","volume":"236","author":"Khatamsaz","year":"2022","journal-title":"Acta Mater."},{"key":"mlstadb53cbib15","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41524-022-00779-7","article-title":"Composition design of high-entropy alloys with deep sets learning","volume":"8","author":"Zhang","year":"2022","journal-title":"npj Comput. Mater."},{"key":"mlstadb53cbib16","doi-asserted-by":"publisher","DOI":"10.1063\/5.0109491","article-title":"Machine learning-based inverse design for single-phase high entropy alloys","volume":"10","author":"Zeng","year":"2022","journal-title":"APL Mater."},{"key":"mlstadb53cbib17","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1126\/science.abo4940","article-title":"Machine learning\u2013enabled high-entropy alloy discovery","volume":"378","author":"Rao","year":"2022","journal-title":"Science"},{"key":"mlstadb53cbib18","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1016\/j.dib.2018.10.071","article-title":"Comprehensive data compilation on the mechanical properties of refractory high-entropy alloys","volume":"21","author":"Couzini\u00e9","year":"2018","journal-title":"Data Brief."},{"key":"mlstadb53cbib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.electacta.2023.143722","article-title":"Machine learning\u2013informed development of high entropy alloys with enhanced corrosion resistance","volume":"476","author":"Ozdemir","year":"2024","journal-title":"Electrochim. Acta"},{"key":"mlstadb53cbib20","first-page":"pp 27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume":"vol 34","author":"Fifty","year":"2021"},{"key":"mlstadb53cbib21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3679013","article-title":"Multi-task learning in natural language processing: an overview","volume":"56","author":"Chen","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"mlstadb53cbib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100238","article-title":"Polymer informatics with multi-task learning","volume":"2","author":"Kuenneth","year":"2021","journal-title":"Patterns"},{"article-title":"Auxiliary tasks in multi-task learning","year":"2018","author":"Liebel","key":"mlstadb53cbib23"},{"key":"mlstadb53cbib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2023.112460","article-title":"Investigating representation schemes for surrogate modeling of high entropy alloys","volume":"230","author":"Debnath","year":"2023","journal-title":"Comput. Mater. Sci."},{"article-title":"Efficient materials informatics between rockets and electrons","year":"2024","author":"Krajewski","key":"mlstadb53cbib25"},{"key":"mlstadb53cbib26","doi-asserted-by":"publisher","first-page":"6731","DOI":"10.21105\/joss.06731","article-title":"nimcso: a nim package for compositional space optimization","volume":"9","author":"Krajewski","year":"2024","journal-title":"J. Open Source Softw."},{"key":"mlstadb53cbib27","first-page":"pp 785","article-title":"Xgboost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"mlstadb53cbib28","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad55a4","article-title":"Explainable machine learning assisted molecular-level insights for enhanced specific stiffness exploiting the large compositional space of alcocrfeni high entropy alloys","volume":"5","author":"Gupta","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"article-title":"Learning sparse neural networks through l0 regularization","year":"2017","author":"Louizos","key":"mlstadb53cbib29"},{"key":"mlstadb53cbib30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2024.116973","article-title":"Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics","volume":"426","author":"Niklas Fuhg","year":"2024","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"mlstadb53cbib31","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14250144","article-title":"Code and data for \u2018overcoming sparse datasets with multi-task learning as applied to high entropy alloys","author":"Debnath","year":"2025"},{"article-title":"Task weighting through gradient projection for multitask learning","year":"2024","author":"Bohn","key":"mlstadb53cbib32"},{"key":"mlstadb53cbib33","first-page":"pp 270","article-title":"Dynamic task prioritization for multitask learning","author":"Guo","year":"2018"},{"key":"mlstadb53cbib34","first-page":"pp 3854","article-title":"Learning to branch for multi-task learning","author":"Guo","year":"2020"},{"key":"mlstadb53cbib35","doi-asserted-by":"publisher","DOI":"10.1016\/j.msea.2024.147446","article-title":"Mechanical properties of pure elements from a comprehensive first-principles study to data-driven insights","volume":"918","author":"Shang","year":"2024","journal-title":"Mater. Sci. Eng. A"},{"key":"mlstadb53cbib36","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.cpc.2016.08.013","article-title":"Miedema calculator: A thermodynamic platform for predicting formation enthalpies of alloys within framework of miedema\u2019s theory","volume":"209","author":"Zhang","year":"2016","journal-title":"Comput. Phys. Commun."},{"key":"mlstadb53cbib37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalmes.2024.100128","article-title":"Data-driven design of high bulk modulus high entropy alloys using machine learning","volume":"8","author":"Jain","year":"2024","journal-title":"J. Alloys Metall. Mater."},{"key":"mlstadb53cbib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2024.112797","article-title":"Predicting and understanding the ductility of BCC high entropy alloys via knowledge-integrated machine learning","volume":"239","author":"Huang","year":"2024","journal-title":"Mater. Des."},{"key":"mlstadb53cbib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2024.113326","article-title":"Machine learning-assisted design of refractory high-entropy alloys with targeted yield strength and fracture strain","volume":"246","author":"He","year":"2024","journal-title":"Mater. Des."},{"key":"mlstadb53cbib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2024.112634","article-title":"Machine learning assisted design of high-entropy alloys with ultra-high microhardness and unexpected low density","volume":"238","author":"Zhao","year":"2024","journal-title":"Mater. Des."},{"key":"mlstadb53cbib41","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-62759-9","article-title":"On exploiting nonparametric kernel-based probabilistic machine learning over the large compositional space of high entropy alloys for optimal nanoscale ballistics","volume":"14","author":"Gupta","year":"2024","journal-title":"Sci. Rep."},{"key":"mlstadb53cbib42","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/BF01397292","article-title":"Zur theorie der elastizit\u00e4tsgrenze und der festigkeit kristallinischer k\u00f6rper","volume":"37","author":"Frenkel","year":"1926","journal-title":"Z. Phys."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T14:32:19Z","timestamp":1740061939000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adb53c"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,20]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,2,20]]},"published-print":{"date-parts":[[2025,3,31]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adb53c","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,2,20]]},"assertion":[{"value":"Overcoming sparse datasets with multi-task learning as applied to high entropy alloys","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-12-05","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-02-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-02-20","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}