{"id":"https://openalex.org/W3105590657","doi":"https://doi.org/10.1145/3388440.3412458","title":"Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation","display_name":"Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3105590657","doi":"https://doi.org/10.1145/3388440.3412458","mag":"3105590657"},"language":"en","primary_location":{"id":"doi:10.1145/3388440.3412458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388440.3412458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018185046","display_name":"Chaochao Yan","orcid":"https://orcid.org/0000-0001-8370-0966"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaochao Yan","raw_affiliation_strings":["The University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371324","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0003-4210-1670"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":["The University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049718088","display_name":"Jinyu Yang","orcid":"https://orcid.org/0000-0002-7004-3570"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Yang","raw_affiliation_strings":["The University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005345630","display_name":"Tingyang Xu","orcid":"https://orcid.org/0000-0002-8487-9045"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyang Xu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068865316","display_name":"Junzhou Huang","orcid":"https://orcid.org/0000-0002-9548-1227"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junzhou Huang","raw_affiliation_strings":["The University of Texas at Arlington, Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Tencent AI Lab","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018185046"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":2.3193,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.89112228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9991999864578247,"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":0.9991999864578247,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9951000213623047,"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"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8289831876754761},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7157384157180786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6764324903488159},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6592100262641907},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5189239978790283},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5130676031112671},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49845337867736816},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41480302810668945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36359965801239014},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.14561191201210022},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.14116805791854858},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13814368844032288}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8289831876754761},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7157384157180786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6764324903488159},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6592100262641907},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5189239978790283},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5130676031112671},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49845337867736816},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41480302810668945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36359965801239014},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.14561191201210022},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14116805791854858},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13814368844032288},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3388440.3412458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388440.3412458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1757990252","https://openalex.org/W1909320841","https://openalex.org/W2023818227","https://openalex.org/W2131774270","https://openalex.org/W2529996553","https://openalex.org/W2749279690","https://openalex.org/W2753738274","https://openalex.org/W2786722833","https://openalex.org/W2798898313","https://openalex.org/W2924334974","https://openalex.org/W2963223306","https://openalex.org/W2964168257","https://openalex.org/W3098269892","https://openalex.org/W4289436753"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2966686650"],"abstract_inverted_index":{"Molecule":[0],"generation":[1],"is":[2],"to":[3,13,78,91],"design":[4],"new":[5],"molecules":[6,24,39],"with":[7],"specific":[8],"chemical":[9,17],"properties":[10],"and":[11,32,82,88,99,108,116,125],"further":[12],"optimize":[14],"the":[15,29,35,41,48,53,59,64,71,79,97,101,121,130,142,148],"desired":[16],"properties.":[18],"Following":[19],"previous":[20],"work,":[21],"we":[22,67,83,104],"encode":[23],"into":[25,38],"continuous":[26],"vectors":[27,37],"in":[28,111],"latent":[30],"space":[31],"then":[33],"decode":[34],"embedding":[36],"under":[40],"variational":[42],"autoencoder":[43],"(VAE)":[44],"framework.":[45],"We":[46],"investigate":[47],"posterior":[49,80,102],"collapse":[50],"problem":[51,98],"of":[52,75],"current":[54],"widely-used":[55],"RNN-based":[56],"VAEs":[57,76],"for":[58],"molecule":[60,139],"sequence":[61],"generation.":[62],"For":[63],"first":[65],"time,":[66],"point":[68],"out":[69],"that":[70],"underestimated":[72],"reconstruction":[73,123],"loss":[74],"leads":[77],"collapse,":[81,103],"also":[84],"provide":[85],"both":[86],"analytical":[87],"experimental":[89],"evidences":[90],"support":[92],"our":[93,118,153],"findings.":[94],"To":[95],"fix":[96],"avoid":[100],"propose":[105],"an":[106],"effective":[107],"efficient":[109],"solution":[110],"this":[112],"work.":[113],"Without":[114],"bells":[115],"whistles,":[117],"method":[119,154],"achieves":[120],"state-of-the-art":[122],"accuracy":[124],"competitive":[126],"validity":[127],"score":[128],"on":[129,159],"ZINC":[131],"250K":[132],"dataset.":[133],"When":[134],"generating":[135],"10,000":[136],"unique":[137],"valid":[138],"sequences":[140],"from":[141],"random":[143],"prior":[144],"sampling,":[145],"it":[146],"costs":[147],"JT-VAE":[149],"1450":[150],"seconds":[151,158],"while":[152],"only":[155],"needs":[156],"9":[157],"a":[160],"regular":[161],"desktop":[162],"machine.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}