{"id":"https://openalex.org/W4396843744","doi":"https://doi.org/10.1145/3589335.3651470","title":"Are we Making Much Progress? Revisiting Chemical Reaction Yield Prediction from an Imbalanced Regression Perspective","display_name":"Are we Making Much Progress? Revisiting Chemical Reaction Yield Prediction from an Imbalanced Regression Perspective","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843744","doi":"https://doi.org/10.1145/3589335.3651470"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3651470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651470","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651470","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651470","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008871638","display_name":"Yihong Ma","orcid":"https://orcid.org/0000-0003-4729-5953"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yihong Ma","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"raw_orcid":"https://orcid.org/0000-0003-4729-5953","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833672","display_name":"Xiaobao Huang","orcid":"https://orcid.org/0009-0002-1679-3888"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobao Huang","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"raw_orcid":"https://orcid.org/0009-0002-1679-3888","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023104692","display_name":"Bozhao Nan","orcid":"https://orcid.org/0000-0001-9645-0724"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bozhao Nan","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"raw_orcid":"https://orcid.org/0000-0001-9645-0724","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047689411","display_name":"Nuno Moniz","orcid":"https://orcid.org/0000-0003-4322-1076"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nuno Moniz","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"raw_orcid":"https://orcid.org/0000-0003-4322-1076","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangliang Zhang","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"raw_orcid":"https://orcid.org/0000-0002-3574-5665","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029114040","display_name":"Olaf Wiest","orcid":"https://orcid.org/0000-0001-9316-7720"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olaf Wiest","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"raw_orcid":"https://orcid.org/0000-0001-9316-7720","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068157871","display_name":"Nitesh V. Chawla","orcid":"https://orcid.org/0000-0003-3932-5956"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitesh V. Chawla","raw_affiliation_strings":["University of Notre Dame, Notre Dame, USA"],"raw_orcid":"https://orcid.org/0000-0003-3932-5956","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":1.8757,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86505655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"790","last_page":"793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9559000134468079,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9559000134468079,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9492999911308289,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11423","display_name":"Pesticide Residue Analysis and Safety","score":0.9394000172615051,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6993129849433899},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5910007357597351},{"id":"https://openalex.org/keywords/yield","display_name":"Yield (engineering)","score":0.584854781627655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5094569325447083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4920367896556854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47401294112205505},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4313647747039795},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.27446359395980835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.249128520488739},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12578049302101135}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6993129849433899},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5910007357597351},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.584854781627655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5094569325447083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4920367896556854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47401294112205505},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4313647747039795},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27446359395980835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.249128520488739},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12578049302101135},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589335.3651470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651470","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651470","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651470","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651470","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843744.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W70001371","https://openalex.org/W4324122028","https://openalex.org/W4367048706","https://openalex.org/W4385568380"],"related_works":["https://openalex.org/W31220157","https://openalex.org/W2312753042","https://openalex.org/W4289356671","https://openalex.org/W2389155397","https://openalex.org/W2165884543","https://openalex.org/W3186837933","https://openalex.org/W2368989808","https://openalex.org/W2034959125","https://openalex.org/W2355687852","https://openalex.org/W2621086889"],"abstract_inverted_index":{"The":[0],"yield":[1,25,53,64,125,132,146,157,179],"of":[2,9,78,100,178],"a":[3,136],"chemical":[4,22],"reaction":[5,118,156],"quantifies":[6],"the":[7,10,17,21,62,89,97,117,151,176],"percentage":[8],"target":[11],"product":[12],"formed":[13],"in":[14,52,70,92,116],"relation":[15],"to":[16,45,57,81,109,129,154],"reactants":[18],"consumed":[19],"during":[20,34],"reaction.":[23],"Accurate":[24],"prediction":[26,54,126,147,158,180],"can":[27,173],"guide":[28],"chemists":[29],"toward":[30],"selecting":[31],"high-yield":[32,74,93,184],"reactions":[33],"synthesis":[35],"planning,":[36],"offering":[37],"valuable":[38],"insights":[39],"before":[40],"dedicating":[41],"time":[42],"and":[43,113],"resources":[44],"wet":[46],"lab":[47],"experiments.":[48],"While":[49],"recent":[50],"advancements":[51],"have":[55],"led":[56],"overall":[58],"performance":[59,90,177],"improvement":[60],"across":[61],"entire":[63],"range,":[65],"an":[66,160],"open":[67],"challenge":[68],"remains":[69],"enhancing":[71],"predictions":[72,94],"for":[73],"reactions,":[75,106],"which":[76],"are":[77],"greater":[79],"concern":[80],"chemists.":[82],"In":[83],"this":[84,121],"paper,":[85],"we":[86,149,165],"argue":[87],"that":[88,167],"gap":[91],"results":[95],"from":[96],"imbalanced":[98,161],"distribution":[99],"real-world":[101,145],"data":[102,122],"skewed":[103],"towards":[104],"low-yield":[105],"often":[107],"due":[108],"unreacted":[110],"starting":[111],"materials":[112],"inherent":[114],"ambiguities":[115],"processes.":[119],"Despite":[120],"imbalance,":[123],"existing":[124],"methods":[127,172],"continue":[128],"treat":[130],"different":[131],"ranges":[133],"equally,":[134],"assuming":[135],"balanced":[137],"training":[138],"distribution.":[139],"Through":[140],"extensive":[141],"experiments":[142],"on":[143,182],"three":[144],"datasets,":[148],"emphasize":[150],"urgent":[152],"need":[153],"reframe":[155],"as":[159],"regression":[162],"problem.":[163],"Finally,":[164],"demonstrate":[166],"incorporating":[168],"simple":[169],"cost-sensitive":[170],"re-weighting":[171],"significantly":[174],"enhance":[175],"models":[181],"underrepresented":[183],"regions.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}