{"id":"https://openalex.org/W4381587374","doi":"https://doi.org/10.48550/arxiv.2306.10060","title":"MUBen: Benchmarking the Uncertainty of Molecular Representation Models","display_name":"MUBen: Benchmarking the Uncertainty of Molecular Representation Models","publication_year":2023,"publication_date":"2023-06-14","ids":{"openalex":"https://openalex.org/W4381587374","doi":"https://doi.org/10.48550/arxiv.2306.10060"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.10060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.10060","pdf_url":"https://arxiv.org/pdf/2306.10060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.10060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100676458","display_name":"Yinghao Li","orcid":"https://orcid.org/0009-0000-7926-8939"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Yinghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018639","display_name":"Lingkai Kong","orcid":"https://orcid.org/0000-0001-6480-513X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Lingkai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709853","display_name":"Yuanqi Du","orcid":"https://orcid.org/0000-0003-2988-0374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yuanqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397967","display_name":"Yue Yu","orcid":"https://orcid.org/0000-0002-3683-5208"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063200221","display_name":"Yuchen Zhuang","orcid":"https://orcid.org/0000-0003-4641-894X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Yuchen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101346983","display_name":"Wenhao Mu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu, Wenhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100734332","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-0142-0280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100676458"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9995999932289124,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8567243218421936},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6683211326599121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6634745597839355},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.597916305065155},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.5752851366996765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.457058846950531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4397276043891907},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4278143048286438},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41128796339035034},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3489522933959961},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16272562742233276}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8567243218421936},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6683211326599121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6634745597839355},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.597916305065155},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.5752851366996765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.457058846950531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4397276043891907},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4278143048286438},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41128796339035034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3489522933959961},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16272562742233276},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.10060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.10060","pdf_url":"https://arxiv.org/pdf/2306.10060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.10060","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.10060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.10060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.10060","pdf_url":"https://arxiv.org/pdf/2306.10060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G11240557","display_name":null,"funder_award_id":"MURI N00014-17-1-2656","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G1726583756","display_name":"III: Small: Go Beyond Short-term Dependency and Homogeneity: A General-Purpose Transformer Recipe for Multi-Domain Heterogeneous Sequential Data Analysis","funder_award_id":"2008334","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4504108201","display_name":null,"funder_award_id":"N00014-17-1","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4751570384","display_name":null,"funder_award_id":"4-17-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5397617431","display_name":null,"funder_award_id":"N00014-17-1-2656","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G6369104783","display_name":null,"funder_award_id":"N00014-17-1-2656","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6484623147","display_name":"III: Medium: Collaborative Research: Principled Uncertainty Quantification in Deep Learning Models for Time Series Analysis","funder_award_id":"2106961","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381587374.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W4238897586","https://openalex.org/W1574414179","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W3009056573","https://openalex.org/W4297676672","https://openalex.org/W2989932438","https://openalex.org/W4387297750","https://openalex.org/W2186333919"],"abstract_inverted_index":{"Large":[0],"molecular":[1,15,80,94,114,127],"representation":[2,115],"models":[3,19,116],"pre-trained":[4,81],"on":[5,31,161],"massive":[6],"unlabeled":[7],"data":[8,33],"have":[9,75],"shown":[10],"great":[11],"success":[12],"in":[13,28,164],"predicting":[14],"properties.":[16],"However,":[17],"these":[18],"may":[20],"tend":[21],"to":[22,52,69,78,117],"overfit":[23],"the":[24,38,54,83,139],"fine-tuning":[25,122],"data,":[26],"resulting":[27],"over-confident":[29],"predictions":[30],"test":[32],"that":[34],"fall":[35],"outside":[36],"of":[37,57,66,85,141],"training":[39,145],"distribution.":[40],"To":[41,99],"address":[42,100],"this":[43,101],"issue,":[44],"uncertainty":[45,95],"quantification":[46],"(UQ)":[47],"methods":[48,91,110,133],"can":[49,158],"be":[50],"used":[51],"improve":[53,79],"models'":[55],"calibration":[56],"predictions.":[58],"Although":[59],"many":[60],"UQ":[61,77,90,109,132,153],"approaches":[62],"exist,":[63],"not":[64],"all":[65],"them":[67],"lead":[68],"improved":[70],"performance.":[71],"While":[72],"some":[73],"studies":[74],"included":[76],"models,":[82,156],"process":[84],"selecting":[86,152],"suitable":[87],"backbone":[88,113,155],"and":[89,144,170],"for":[92,111,151,154],"reliable":[93],"estimation":[96],"remains":[97],"underexplored.":[98],"gap,":[102],"we":[103,137],"present":[104],"MUBen,":[105],"which":[106,157],"evaluates":[107],"different":[108,126,135],"state-of-the-art":[112],"investigate":[118],"their":[119],"capabilities.":[120],"By":[121],"various":[123],"backbones":[124],"using":[125],"descriptors":[128],"as":[129,167],"inputs":[130],"with":[131],"from":[134],"categories,":[136],"assess":[138],"influence":[140],"architectural":[142],"decisions":[143],"strategies.":[146],"Our":[147],"study":[148],"offers":[149],"insights":[150],"facilitate":[159],"research":[160],"uncertainty-critical":[162],"applications":[163],"fields":[165],"such":[166],"materials":[168],"science":[169],"drug":[171],"discovery.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}