{"id":"https://openalex.org/W4391452033","doi":"https://doi.org/10.1021/acs.jcim.3c00919","title":"Pretraining Strategies for Structure Agnostic Material Property Prediction","display_name":"Pretraining Strategies for Structure Agnostic Material Property Prediction","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4391452033","doi":"https://doi.org/10.1021/acs.jcim.3c00919","pmid":"https://pubmed.ncbi.nlm.nih.gov/38301621"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00919","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00919","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00919","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00919","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101588975","display_name":"Hongshuo Huang","orcid":"https://orcid.org/0000-0002-7405-7689"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongshuo Huang","raw_affiliation_strings":["Department of Material Science and Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States"],"raw_orcid":"https://orcid.org/0000-0002-7405-7689","affiliations":[{"raw_affiliation_string":"Department of Material Science and Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011452751","display_name":"Rishikesh Magar","orcid":"https://orcid.org/0000-0001-6216-0518"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishikesh Magar","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States"],"raw_orcid":"https://orcid.org/0000-0001-6216-0518","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008745801","display_name":"Amir Barati Farimani","orcid":"https://orcid.org/0000-0002-2952-8576"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amir Barati Farimani","raw_affiliation_strings":["Department of Material Science and Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States"],"raw_orcid":"https://orcid.org/0000-0002-2952-8576","affiliations":[{"raw_affiliation_string":"Department of Material Science and Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008745801"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.5523,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85743323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"64","issue":"3","first_page":"627","last_page":"637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10736","display_name":"Hydrogen embrittlement and corrosion behaviors in metals","score":0.9666000008583069,"subfield":{"id":"https://openalex.org/subfields/2506","display_name":"Metals and Alloys"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8293709754943848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8060362935066223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6949479579925537},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.6545944213867188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6280784010887146},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5770459771156311},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49048563838005066},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49039554595947266},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4446243643760681},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4360431730747223},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41717594861984253},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3235170245170593},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1577381193637848}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8293709754943848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060362935066223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6949479579925537},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6545944213867188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6280784010887146},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5770459771156311},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49048563838005066},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49039554595947266},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4446243643760681},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4360431730747223},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41717594861984253},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3235170245170593},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1577381193637848},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.3c00919","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00919","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00919","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:38301621","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38301621","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10865364","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10865364","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10865364/pdf/ci3c00919.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.3c00919","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00919","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00919","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391452033.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1964746686","https://openalex.org/W1992985800","https://openalex.org/W2000290293","https://openalex.org/W2029413789","https://openalex.org/W2112845989","https://openalex.org/W2130055919","https://openalex.org/W2464725281","https://openalex.org/W2530960271","https://openalex.org/W2582500555","https://openalex.org/W2612591418","https://openalex.org/W2733963201","https://openalex.org/W2766518642","https://openalex.org/W2766856748","https://openalex.org/W2778051509","https://openalex.org/W2801006326","https://openalex.org/W2804431384","https://openalex.org/W2949095042","https://openalex.org/W2950890616","https://openalex.org/W2953641512","https://openalex.org/W2964046296","https://openalex.org/W2968923792","https://openalex.org/W2978707075","https://openalex.org/W3007550778","https://openalex.org/W3013732669","https://openalex.org/W3023937119","https://openalex.org/W3049517558","https://openalex.org/W3098062507","https://openalex.org/W3100220443","https://openalex.org/W3100710928","https://openalex.org/W3101131029","https://openalex.org/W3103227378","https://openalex.org/W3104644561","https://openalex.org/W3113009196","https://openalex.org/W3116783766","https://openalex.org/W3208687975","https://openalex.org/W3210142335","https://openalex.org/W3212512279","https://openalex.org/W3214987860","https://openalex.org/W4221149339","https://openalex.org/W4221151574","https://openalex.org/W4223910234","https://openalex.org/W4234552385","https://openalex.org/W4288050273","https://openalex.org/W4308919251","https://openalex.org/W4309594747","https://openalex.org/W4318262876","https://openalex.org/W4362737433","https://openalex.org/W6600339963","https://openalex.org/W6600631999","https://openalex.org/W6600713050","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W4236696095","https://openalex.org/W3143779693","https://openalex.org/W2626808643","https://openalex.org/W2004064826","https://openalex.org/W3103727510","https://openalex.org/W97045569","https://openalex.org/W2611989081","https://openalex.org/W1527069879","https://openalex.org/W2946179579"],"abstract_inverted_index":{"In":[0,141],"recent":[1],"years,":[2],"machine":[3],"learning":[4,133,175,178,182],"(ML),":[5],"especially":[6],"graph":[7],"neural":[8],"network":[9],"(GNN)":[10],"models,":[11],"has":[12],"been":[13,68],"successfully":[14],"used":[15,98,153],"for":[16,36,55,191,228],"fast":[17],"and":[18,47,89,94,180,184,208],"accurate":[19,37,229],"prediction":[20,167],"of":[21,102,130,219],"material":[22,165,230],"properties.":[23],"However,":[24,82],"most":[25],"ML":[26],"models":[27,56,104],"rely":[28,58],"on":[29,59,76,124,188],"relaxed":[30,41],"crystal":[31,42],"structures":[32,43],"to":[33,108,154,160],"develop":[34],"descriptors":[35,73,85],"predictions.":[38],"Generating":[39],"these":[40,156],"can":[44,120,151],"be":[45,152],"expensive":[46],"time-consuming,":[48],"thus":[49],"requiring":[50],"an":[51],"additional":[52],"processing":[53],"step":[54],"that":[57,119,150,223],"them.":[60],"To":[61],"address":[62],"this":[63,142],"challenge,":[64],"structure-agnostic":[65,139,197],"methods":[66],"have":[67,109,115],"developed,":[69],"which":[70,105],"use":[71],"fixed-length":[72,84],"engineered":[74],"based":[75,123],"human":[77],"knowledge":[78,93],"about":[79],"the":[80,83,100,128,163,192,212,217],"material.":[81],"are":[86,96,106],"often":[87],"hand-engineered":[88],"require":[90],"extensive":[91],"domain":[92],"generally":[95],"not":[97],"in":[99,204,211],"context":[101],"learnable":[103,117,158],"known":[107],"a":[110,195],"superior":[111],"performance.":[112,168],"Recent":[113],"advancements":[114],"proposed":[116],"frameworks":[118,134,159],"construct":[121],"representations":[122],"stoichiometry":[125],"alone,":[126],"allowing":[127],"flexibility":[129],"using":[131],"deep":[132],"as":[135,137,173],"well":[136],"leveraging":[138],"learning.":[140],"work,":[143],"we":[144],"propose":[145],"three":[146],"different":[147],"pretraining":[148],"strategies":[149,171,222],"pretrain":[155,221],"structure-agnostic,":[157],"further":[161],"improve":[162],"downstream":[164,189],"property":[166,231],"We":[169],"incorporate":[170],"such":[172],"self-supervised":[174],"(SSL),":[176],"fingerprint":[177],"(FL),":[179],"multimodal":[181],"(ML)":[183],"demonstrate":[185],"their":[186],"efficacy":[187],"tasks":[190],"Roost":[193],"architecture,":[194],"popular":[196],"framework.":[198],"Our":[199],"results":[200],"show":[201],"significant":[202],"improvement":[203],"small":[205],"data":[206,209,214,227],"sets":[207],"efficiency":[210],"larger":[213],"sets,":[215],"underscoring":[216],"potential":[218],"our":[220],"effectively":[224],"leverage":[225],"unlabeled":[226],"prediction.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}