{"id":"https://openalex.org/W4403578258","doi":"https://doi.org/10.48550/arxiv.2410.12522","title":"MING: A Functional Approach to Learning Molecular Generative Models","display_name":"MING: A Functional Approach to Learning Molecular Generative Models","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403578258","doi":"https://doi.org/10.48550/arxiv.2410.12522"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.12522","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.12522","pdf_url":"https://arxiv.org/pdf/2410.12522","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.12522","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070289435","display_name":"Van Khoa Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210088449","display_name":"HES-SO Gen\u00e8ve","ror":"https://ror.org/007gfwn20","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210088449"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nguyen, Van Khoa","raw_affiliation_strings":["HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva","institution_ids":["https://openalex.org/I4210088449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055063265","display_name":"Maciej Falkiewicz","orcid":"https://orcid.org/0000-0002-3851-1995","observed_orcids":["https://orcid.org/0000-0002-3851-1995"]},"institutions":[{"id":"https://openalex.org/I4210088449","display_name":"HES-SO Gen\u00e8ve","ror":"https://ror.org/007gfwn20","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210088449"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Falkiewicz, Maciej","raw_affiliation_strings":["HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva","institution_ids":["https://openalex.org/I4210088449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019371444","display_name":"Giangiacomo Mercatali","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210088449","display_name":"HES-SO Gen\u00e8ve","ror":"https://ror.org/007gfwn20","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210088449"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mercatali, Giangiacomo","raw_affiliation_strings":["HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva","institution_ids":["https://openalex.org/I4210088449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084831490","display_name":"Alexandros Kalousis","orcid":"https://orcid.org/0000-0001-6282-0686","observed_orcids":["https://orcid.org/0000-0001-6282-0686","https://orcid.org/0000-0001-9734-195X"]},"institutions":[{"id":"https://openalex.org/I4210088449","display_name":"HES-SO Gen\u00e8ve","ror":"https://ror.org/007gfwn20","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210088449"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kalousis, Alexandros","raw_affiliation_strings":["HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HES-SO Geneva University of Geneva HES-SO Geneva University of Geneva HES-SO Geneva HES-SO Geneva","institution_ids":["https://openalex.org/I4210088449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210088449"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.020400000736117363,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/molecular-generation","display_name":"molecular generation","score":0.7099999785423279},{"id":"https://openalex.org/keywords/implicit-neural-representations","display_name":"implicit neural representations","score":0.734000027179718},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.9380000233650208},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.8050000071525574},{"id":"https://openalex.org/keywords/latent-space","display_name":"latent space","score":0.3580000102519989},{"id":"https://openalex.org/keywords/molecular-distribution","display_name":"molecular distribution","score":0.5830000042915344},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6179999709129333}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7920239567756653},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45707187056541443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42222100496292114},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.41468819975852966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.390055775642395},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36770856380462646}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2410.12522","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.12522","pdf_url":"https://arxiv.org/pdf/2410.12522","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"pmh:oai:hesso.tind.io:17042","doi":null,"is_oa":true,"landing_page_url":"https://proceedings.mlr.press/v258/nguyen25c.html","pdf_url":"https://raw.githubusercontent.com/mlresearch/v258/main/assets/nguyen25c/nguyen25c.pdf","source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/17042","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2410.12522","doi":"https://doi.org/10.48550/arxiv.2410.12522","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.12522","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.12522","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.12522","pdf_url":"https://arxiv.org/pdf/2410.12522","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G116443652","display_name":"Learning generative models for molecules","funder_award_id":"207428","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320323830","display_name":"Universit\u00e9 de Gen\u00e8ve","ror":"https://ror.org/01swzsf04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403578258.pdf","grobid_xml":"https://content.openalex.org/works/W4403578258.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2806351858","https://openalex.org/W2994860160","https://openalex.org/W2996064569","https://openalex.org/W3126517808","https://openalex.org/W3190965961","https://openalex.org/W4320461342","https://openalex.org/W4320854419"],"related_works":["https://openalex.org/W4393866501","https://openalex.org/W6929253169","https://openalex.org/W4408149544","https://openalex.org/W4402500708","https://openalex.org/W4367625386","https://openalex.org/W3181844989","https://openalex.org/W4415250942","https://openalex.org/W7126019849","https://openalex.org/W4412830033","https://openalex.org/W4221145170"],"abstract_inverted_index":{"Traditional":[0],"molecule":[1,30],"generation":[2,140],"methods":[3,130],"often":[4],"rely":[5],"on":[6,34,113],"sequence-":[7],"or":[8,17],"graph-based":[9],"representations,":[10],"which":[11,72],"can":[12],"limit":[13],"their":[14],"expressive":[15],"power":[16],"require":[18],"complex":[19],"permutation-equivariant":[20],"architectures.":[21],"This":[22,96],"paper":[23],"introduces":[24],"a":[25,45,66,99,133],"novel":[26,67],"paradigm":[27],"for":[28,89],"learning":[29],"generative":[31],"models":[32],"based":[33],"functional":[35,68],"representations.":[36],"Specifically,":[37],"we":[38],"propose":[39],"Molecular":[40],"Implicit":[41],"Neural":[42],"Generation":[43],"(MING),":[44],"diffusion-based":[46],"model":[47,103],"that":[48,105],"learns":[49],"molecular":[50,125],"distributions":[51],"in":[52,60,76],"the":[53,61,78],"function":[54,109],"space.":[55],"Unlike":[56],"standard":[57],"diffusion":[58],"processes":[59],"data":[62],"space,":[63],"MING":[64],"employs":[65],"denoising":[69],"probabilistic":[70],"process,":[71],"jointly":[73],"denoises":[74],"information":[75],"both":[77],"function's":[79],"input":[80],"and":[81,120,137],"output":[82],"spaces":[83],"by":[84],"leveraging":[85],"an":[86],"expectation-maximization":[87],"procedure":[88],"latent":[90],"implicit":[91],"neural":[92],"representations":[93],"of":[94],"data.":[95],"approach":[97],"enables":[98],"simple":[100],"yet":[101],"effective":[102],"design":[104],"accurately":[106],"captures":[107],"underlying":[108],"distributions.":[110],"Experimental":[111],"results":[112],"molecule-related":[114],"datasets":[115],"demonstrate":[116],"MING's":[117],"superior":[118],"performance":[119],"ability":[121],"to":[122],"generate":[123],"plausible":[124],"samples,":[126],"surpassing":[127],"state-of-the-art":[128],"data-space":[129],"while":[131],"offering":[132],"more":[134],"streamlined":[135],"architecture":[136],"significantly":[138],"faster":[139],"times.":[141],"The":[142],"code":[143],"is":[144],"available":[145],"at":[146],"https://github.com/v18nguye/MING.":[147]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-10-20T00:00:00"}