{"id":"https://openalex.org/W4403582625","doi":"https://doi.org/10.1145/3627673.3679607","title":"Vision Language Model is NOT All You Need: Augmentation Strategies for Molecule Language Models","display_name":"Vision Language Model is NOT All You Need: Augmentation Strategies for Molecule Language Models","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582625","doi":"https://doi.org/10.1145/3627673.3679607"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679607","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627673.3679607","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085288448","display_name":"Namkyeong Lee","orcid":"https://orcid.org/0000-0003-3995-1148"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namkyeong Lee","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-3995-1148","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061746697","display_name":"Siddhartha Laghuvarapu","orcid":"https://orcid.org/0000-0002-1269-3778"},"institutions":[{"id":"https://openalex.org/I183874917","display_name":"Urbana University","ror":"https://ror.org/04kp3hw27","country_code":"US","type":"education","lineage":["https://openalex.org/I183874917"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Laghuvarapu","raw_affiliation_strings":["UIUC, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-1269-3778","affiliations":[{"raw_affiliation_string":"UIUC, Urbana, IL, USA","institution_ids":["https://openalex.org/I183874917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101629748","display_name":"Chanyoung Park","orcid":"https://orcid.org/0000-0002-5957-5816"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanyoung Park","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5957-5816","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084279065","display_name":"Jimeng Sun","orcid":"https://orcid.org/0000-0003-1512-6426"},"institutions":[{"id":"https://openalex.org/I183874917","display_name":"Urbana University","ror":"https://ror.org/04kp3hw27","country_code":"US","type":"education","lineage":["https://openalex.org/I183874917"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimeng Sun","raw_affiliation_strings":["UIUC, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-1512-6426","affiliations":[{"raw_affiliation_string":"UIUC, Urbana, IL, USA","institution_ids":["https://openalex.org/I183874917"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3205,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63486606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1153","last_page":"1162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9983000159263611,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9775999784469604,"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/computer-science","display_name":"Computer science","score":0.7376081943511963},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5514779686927795},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4301377832889557},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.4226805567741394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36691713333129883},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3036925196647644},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06976896524429321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376081943511963},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5514779686927795},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4301377832889557},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.4226805567741394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36691713333129883},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3036925196647644},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06976896524429321}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679607","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679607","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W170237590","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W2116759194","https://openalex.org/W2151697120","https://openalex.org/W2156077095","https://openalex.org/W2767891136","https://openalex.org/W3015572666","https://openalex.org/W3080997787","https://openalex.org/W3095883070","https://openalex.org/W3097145107","https://openalex.org/W3175593095","https://openalex.org/W3211951295","https://openalex.org/W4206347812","https://openalex.org/W4283796586","https://openalex.org/W4292939076","https://openalex.org/W4297458751","https://openalex.org/W4385568311","https://openalex.org/W4389888290"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W4231937131","https://openalex.org/W3188962172","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W2772917594","https://openalex.org/W1487966966","https://openalex.org/W4312825515","https://openalex.org/W3204019825","https://openalex.org/W2107238869"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"a":[4,58,118],"growing":[5],"interest":[6],"among":[7,78,113],"researchers":[8],"in":[9,50,156,167],"understanding":[10],"molecules":[11,116,135,158],"and":[12,65,97,159],"their":[13,160],"textual":[14],"descriptions":[15,112],"through":[16],"molecule":[17],"language":[18,38],"models":[19,39],"(MoLM).":[20],"However,":[21],"despite":[22],"some":[23],"early":[24],"promising":[25],"developments,":[26],"the":[27,51,73,79,100,103,152],"advancement":[28],"of":[29,36,53,61,76,154],"MoLM":[30,54],"still":[31],"trails":[32],"significantly":[33],"behind":[34],"that":[35,69,136],"vision":[37],"(VLM).":[40],"This":[41],"is":[42,176],"because":[43],"unique":[44],"challenges":[45],"exist":[46],"apart":[47],"from":[48,134],"VLM":[49],"field":[52],"due":[55,71],"to":[56,72,131,140],"1)":[57,88],"limited":[59],"amount":[60],"molecule-text":[62,90,108],"paired":[63],"data":[64],"2)":[66,98],"missing":[67],"expertise":[68,101,128,139],"occurred":[70],"specialized":[74],"areas":[75],"focus":[77],"experts.":[80],"To":[81],"this":[82],"end,":[83],"we":[84,125],"propose":[85,126],"AMOLE,":[86],"which":[87],"augments":[89],"pairs":[91,109],"with":[92,117,142],"structural":[93,120],"similarity":[94,121],"preserving":[95,122],"loss,":[96],"transfers":[99],"between":[102],"molecules.":[104],"Specifically,":[105],"AMOLE":[106,155,175],"enriches":[107],"by":[110],"sharing":[111],"structurally":[114],"similar":[115],"novel":[119],"loss.":[123],"Moreover,":[124],"an":[127],"reconstruction":[129],"loss":[130],"transfer":[132],"knowledge":[133],"have":[137],"extensive":[138],"those":[141],"less":[143],"expertise.":[144],"Extensive":[145],"experiments":[146],"on":[147],"various":[148],"downstream":[149],"tasks":[150],"demonstrate":[151],"superiority":[153],"comprehending":[157],"descriptions,":[161],"highlighting":[162],"its":[163],"potential":[164],"for":[165,174],"application":[166],"real-world":[168],"drug":[169],"discovery.":[170],"The":[171],"source":[172],"code":[173],"available":[177],"at":[178],"https://github.com/Namkyeong/AMOLE.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}