{"id":"https://openalex.org/W4406508097","doi":"https://doi.org/10.1088/2632-2153/adabb1","title":"Causality-driven feature selection and domain adaptation for enhancing chemical foundation models in downstream tasks","display_name":"Causality-driven feature selection and domain adaptation for enhancing chemical foundation models in downstream tasks","publication_year":2025,"publication_date":"2025-01-17","ids":{"openalex":"https://openalex.org/W4406508097","doi":"https://doi.org/10.1088/2632-2153/adabb1"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/adabb1","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/adabb1","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/adabb1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068590850","display_name":"Eduardo Soares","orcid":"https://orcid.org/0000-0002-2634-8270"},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Eduardo Soares","raw_affiliation_strings":["IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2634-8270","affiliations":[{"raw_affiliation_string":"IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094342765","display_name":"Victor Shirasuna","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Victor Yukio Shirasuna","raw_affiliation_strings":["IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077314929","display_name":"Em\u00edlio Vital Brazil","orcid":"https://orcid.org/0000-0003-4982-3836"},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Emilio Vital Brazil","raw_affiliation_strings":["IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-4982-3836","affiliations":[{"raw_affiliation_string":"IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Karen Fiorella Aquino Gutierrez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Karen Fiorella Aquino Gutierrez","raw_affiliation_strings":["IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109100433","display_name":"Renato Cerqueira","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Renato Cerqueira","raw_affiliation_strings":["IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Rio de Janeiro, Rio de Janeiro 20031-170, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090730388","display_name":"Dmitry Yu. Zubarev","orcid":"https://orcid.org/0000-0001-7961-3149"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry Zubarev","raw_affiliation_strings":["IBM Research, San Jose, CA 95120, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, San Jose, CA 95120, United States of America","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085426538","display_name":"Kristin Schmidt","orcid":"https://orcid.org/0000-0003-1339-841X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristin Schmidt","raw_affiliation_strings":["IBM Research, San Jose, CA 95120, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, San Jose, CA 95120, United States of America","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109872649","display_name":"Daniel Sanders","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel P Sanders","raw_affiliation_strings":["IBM Research, San Jose, CA 95120, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, San Jose, CA 95120, United States of America","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85043335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"6","issue":"1","first_page":"015017","last_page":"015017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.909600019454956,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.909600019454956,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9050999879837036,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.7876780033111572},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6906408071517944},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6138034462928772},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5856465101242065},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5563172101974487},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5322157144546509},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.5297542214393616},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4923325777053833},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4710996747016907},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46468260884284973},{"id":"https://openalex.org/keywords/downstream-processing","display_name":"Downstream processing","score":0.4335750639438629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3401614725589752},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22538414597511292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17946231365203857},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1398448944091797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11343920230865479},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.09401682019233704},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09379968047142029},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.0612066388130188}],"concepts":[{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.7876780033111572},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6906408071517944},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6138034462928772},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5856465101242065},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5563172101974487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5322157144546509},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.5297542214393616},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4923325777053833},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4710996747016907},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46468260884284973},{"id":"https://openalex.org/C67568554","wikidata":"https://www.wikidata.org/wiki/Q385442","display_name":"Downstream processing","level":2,"score":0.4335750639438629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3401614725589752},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22538414597511292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17946231365203857},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1398448944091797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11343920230865479},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.09401682019233704},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09379968047142029},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0612066388130188},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1088/2632-2153/adabb1","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/adabb1","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:10e4d3c4a99342959a644379e57b2010","is_oa":true,"landing_page_url":"https://doaj.org/article/10e4d3c4a99342959a644379e57b2010","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 6, Iss 1, p 015017 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/adabb1","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/adabb1","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W71749367","https://openalex.org/W2159887157","https://openalex.org/W2565684601","https://openalex.org/W2594183968","https://openalex.org/W2791355014","https://openalex.org/W2966357564","https://openalex.org/W2968734407","https://openalex.org/W4200265373","https://openalex.org/W4205259885","https://openalex.org/W4205276693","https://openalex.org/W4213077304","https://openalex.org/W4226159083","https://openalex.org/W4226166856","https://openalex.org/W4313485929","https://openalex.org/W4321458910","https://openalex.org/W4323304388","https://openalex.org/W4377096651","https://openalex.org/W4383373262","https://openalex.org/W6638875480","https://openalex.org/W6679868779","https://openalex.org/W6736685754","https://openalex.org/W6772083016","https://openalex.org/W6779101013","https://openalex.org/W6784614190","https://openalex.org/W6800751262","https://openalex.org/W6802446583","https://openalex.org/W6837036770","https://openalex.org/W6839551828","https://openalex.org/W6843615466","https://openalex.org/W6849048860","https://openalex.org/W6853595509","https://openalex.org/W6856941743","https://openalex.org/W6859298233","https://openalex.org/W6870642166"],"related_works":["https://openalex.org/W1511795264","https://openalex.org/W1534822428","https://openalex.org/W1760094216","https://openalex.org/W4249991114","https://openalex.org/W3097720904","https://openalex.org/W4234307004","https://openalex.org/W1541057343","https://openalex.org/W4245017608","https://openalex.org/W2766573403","https://openalex.org/W3115222093"],"abstract_inverted_index":{"Abstract":[0],"Recent":[1],"advancements":[2],"in":[3,11,72],"large":[4],"foundation":[5,107,164],"models":[6,18,108],"have":[7],"revealed":[8],"impressive":[9],"capabilities":[10],"mastering":[12],"complex":[13],"chemical":[14,53,106],"language":[15,54],"representations.":[16],"These":[17],"undergo":[19],"a":[20,66,91,115],"task-agnostic":[21],"learning":[22],"phase,":[23,81],"characterized":[24],"by":[25,32],"pre-training":[26,80],"on":[27,34,42,109,125,162],"extensive":[28],"unlabeled":[29],"corpora":[30],"followed":[31],"fine-tuning":[33],"specific":[35,130],"downstream":[36,73,110,131],"tasks.":[37,111,157],"This":[38],"methodology":[39],"reduces":[40],"reliance":[41],"labeled":[43],"data,":[44],"facilitating":[45],"data":[46,70],"acquisition":[47],"and":[48,98,137,152,167,176],"broadening":[49],"the":[50,69,79,103,147,174,177],"scope":[51],"of":[52,78,105,180],"representation.":[55],"However,":[56],"real-world":[57],"scenarios":[58],"often":[59],"pose":[60],"challenges":[61],"due":[62],"to":[63,101],"domain":[64,99],"shift,":[65],"phenomenon":[67],"where":[68],"distribution":[71],"tasks":[74],"differs":[75],"from":[76],"that":[77,120],"potentially":[82],"degrading":[83],"model":[84,165],"performance.":[85],"To":[86],"address":[87],"this,":[88],"we":[89],"present":[90],"novel":[92],"causal-based":[93],"framework":[94],"for":[95,155],"feature":[96,117],"selection":[97,118],"adaptation":[100],"enhance":[102],"performance":[104,170],"Our":[112],"approach":[113,143,161],"employs":[114],"multi-stage":[116],"method":[119],"identifies":[121],"physico-chemical":[122],"features":[123,151],"based":[124],"their":[126],"direct":[127],"causal-effect":[128],"over":[129],"properties.":[132],"By":[133],"employing":[134],"Mordred":[135],"descriptors":[136],"Markov":[138],"blanket":[139],"causal":[140,148],"graphs,":[141],"our":[142,160,181],"provides":[144],"insight":[145],"into":[146],"relationships":[149],"between":[150],"target":[153],"properties":[154],"prediction":[156],"We":[158],"evaluate":[159],"various":[163],"architectures":[166],"datasets,":[168],"demonstrating":[169],"improvements,":[171],"which":[172],"showcases":[173],"robustness":[175],"agnostic":[178],"nature":[179],"approach.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}