[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123451-en":3,"doc-seo-123451-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123451,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Fault-tolerant Quantum Chemical Calculations with Improved Machine-Learning Models","Efficient use of computational resources is essential for reliable scientific calculations. Building on prior work on ML-assisted scheduling optimization, this study develops improved machine-learning models to better predict computational loads, enabling more effective load-balancing. It further integrates coded computation via gradient coding to introduce fault tolerance in distributed quantum chemical workflows. The approach is demonstrated using REM-TDDFT-based excited-state calculations and benchmark systems such as P38 protein and solvent models with excitable centers.","arXiv :2401 .09484v3 [physics .chem-ph] 1 Aug 2024  \nFault-tolerant Quantum Chemical Calculations with Improved Machine-Learning Models  \nKai Yuan ‡†¶, Shuai Zhou §‖¶, Ning Li †,†Tianyan Li †, Bowen Ding ‡,‡∗  \nDanhuai Guo ‡∗, Yingjin Ma †∗  \nAugust 5, 2024  \nAbstract  \nEasy and e􀀋ective usage of computational resources is crucial for scienti􀀌c calculations. Following our recent work of machine-learning (ML) assisted scheduling optimization [Ref: J. Comput. Chem. 2023, 44, 1174], we further propose 1) the improved ML models for the better predictions of computational loads, and as such, more elaborate load-balancing calculations can be expected; 2) the idea of coded computation, i.e. the integration of gradient coding, in order to introduce fault tolerance during the distributed calculations; and 3) their applications together with re-normalized exciton model with time-dependent density functional theory (REM-TDDFT) for calculating the excited states. Illustrated benchmark calculations include P38 protein, and solvent model with one or several excitable centers. The results show that the improved ML-assisted coded calculations can further improve the load-balancing and cluster utilization, owing primarily pro􀀌t in fault tolerance that aims at the automated quantum chemical calculations for both ground and excited states.  \nKeywords: Coded computing, load-balancing, interacting energy, fragmented approach,  \nexciton model.  \n¶ Authors contributed to this work equally  \n∗ Corresponding authors: [dingbowen1214@163.com](dingbowen1214@163.com), [gdh@buct.edu.cn](gdh@buct.edu.cn), and[yingjin.ma@sccas.cn](yingjin.ma@sccas.cn)  \n‡College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China  \n†Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China  \n‖Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China  \n§ School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 101408, China  \n††College of Chemistry and Materials Engineering, Wenzhou University, Wenzhou 325035, China  \n‡‡Institute of Chemistry, Chinese Academy of Sciences, Beijing 100190, China  \n(75 words.) We present a procedure for easy and e􀀋ective implementations of coded quantum chemical calculations with improved machine-learning (ML) models. Employing this procedure, we show that the improved ML-assisted coded calculations can further improve the load-balancing and cluster utilization, owing primarily pro􀀌t in fault tolerance that aims at the automated quantum chemical calculations for both ground and excited states.  \n1 Introduction  \nThe primary objective of quantum chemical calculations has always been to provide reliable descriptions of various properties for di􀀋erent molecular systems. However, the complexity of traditional quantum mechanics (QM) methods, particularly the computation of electron repulsion integrals (ERIs) using atomic basis functions, limits their application to large molecular systems. Currently, there is a growing interest in applying quantum chemical calculations to the study of biological macromolecular systems. While QM methods are typically restricted to relatively small systems (tens of atoms), their scope can be expanded using fragment-based techniques 1–10 or linear scaling strategies 11–21 when combined withe􀀎cient load-balancing schemes. For example,the identi􀀌cation of important interactions of the SARS-CoV-2 spike protein at the QM level can be routinely implemented using fragment molecular orbitals (FMO) and molecular fractionation with conjugate caps (MFCC) . 22–27 These advanced computational techniques provide a more detailed understanding of the electronic aspects of large molecules, including bio-pharmaceutical systems 28 .  \nAs exascale supercomputing progresses, high-performance computing (HPC) is playing an increasingly crucial role in scienti􀀌c calculations. Gustafson’s law assert","cbCaiqsr0sefuyod","https://ap.wps.com/l/cbCaiqsr0sefuyod","pdf",1812614,1,40,"English","en",105,"# Introduction\n## Motivation for quantum chemical calculations\n## HPC and parallel computation in quantum chemistry\n## Load balancing and cost prediction strategies\n## ML-assisted parallelization and static load balancing\n## ML methods for computational cost prediction","[{\"question\":\"What improvements do the proposed machine-learning models provide?\",\"answer\":\"The work improves predictions of computational loads, which supports more elaborate and effective load-balancing in quantum chemical calculations.\"},{\"question\":\"How does coded computation contribute to fault tolerance in distributed calculations?\",\"answer\":\"By integrating gradient coding into distributed computation, the method introduces fault tolerance during parallel quantum chemical workflows.\"},{\"question\":\"What excited-state framework is used to apply the combined approach?\",\"answer\":\"The method is applied together with the re-normalized exciton model with time-dependent density functional theory (REM-TDDFT) to calculate excited states.\"}]","Fault-tolerant Quantum Chemical Calculations with Improved Machine-Learning Models | PDF",1785816597,101,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"fault-tolerant-quantum-chemical-calculations-with-improved-machine-learning-models","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/fault-tolerant-quantum-chemical-calculations-with-improved-machine-learning-models/123451/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What improvements do the proposed machine-learning models provide?","Question",{"text":75,"@type":76},"The work improves predictions of computational loads, which supports more elaborate and effective load-balancing in quantum chemical calculations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does coded computation contribute to fault tolerance in distributed calculations?",{"text":80,"@type":76},"By integrating gradient coding into distributed computation, the method introduces fault tolerance during parallel quantum chemical workflows.",{"name":82,"@type":73,"acceptedAnswer":83},"What excited-state framework is used to apply the combined approach?",{"text":84,"@type":76},"The method is applied together with the re-normalized exciton model with time-dependent density functional theory (REM-TDDFT) to calculate excited states.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":21,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]