{"id":"https://openalex.org/W7155035536","doi":"https://doi.org/10.48550/arxiv.2604.16362","title":"SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning","display_name":"SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7155035536","doi":"https://doi.org/10.48550/arxiv.2604.16362"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16362","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16362","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.16362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093204778","display_name":"Nikola Jovi\u0161i\u0107","orcid":"https://orcid.org/0009-0003-3000-2920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jovi\u0161i\u0107, Nikola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043856241","display_name":"Milica \u0160kipina","orcid":"https://orcid.org/0000-0002-9410-901X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u0160kipina, Milica","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120777536","display_name":"Vanja \u0160venda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u0160venda, Vanja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.24799999594688416,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.24799999594688416,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15700000524520874,"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"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.0925000011920929,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.5708000063896179},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5523999929428101},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5519999861717224},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5450000166893005},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5386000275611877},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48159998655319214},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4650000035762787},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4472000002861023},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41280001401901245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322000026702881},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5593000054359436},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5523999929428101},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5450000166893005},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4472000002861023},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.375},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16362","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16362","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.16362","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16362","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data":[0],"scarcity":[1],"and":[2,61,123,131,163,190],"weak":[3],"supervision":[4],"continue":[5],"to":[6,63,103,128,156],"limit":[7],"the":[8,28,41,58,85,91,159,182],"performance":[9,167],"of":[10,40,45,48,135,184],"machine":[11],"learning":[12],"models":[13,34,77],"in":[14,84],"many":[15],"real-world":[16],"applications,":[17],"such":[18,46],"as":[19,53],"mammography,":[20],"where":[21],"Multiple":[22],"Instance":[23],"Learning":[24],"(MIL)":[25],"often":[26],"offers":[27],"best":[29],"formulation.":[30],"While":[31],"recent":[32],"foundation":[33],"provide":[35],"strong":[36],"semantic":[37],"representations":[38,47],"out":[39],"box,":[42],"effective":[43],"augmentation":[44],"MIL":[49,79],"data":[50,161,176],"remains":[51],"limited,":[52],"existing":[54],"methods":[55],"operate":[56],"at":[57],"instance":[59],"level":[60],"fail":[62],"capture":[64],"intra-bag":[65],"dependencies.":[66],"In":[67],"this":[68],"work,":[69],"we":[70],"introduce":[71],"SetFlow,":[72],"a":[73,97,141,146],"generative":[74,186],"architecture":[75],"that":[76],"entire":[78],"bags":[80],"(i.e.,":[81],"sets)":[82],"directly":[83],"representation":[86],"space.":[87],"Our":[88],"approach":[89],"leverages":[90],"flow":[92],"matching":[93],"paradigm":[94],"combined":[95],"with":[96],"Set":[98],"Transformer-inspired":[99],"design,":[100],"enabling":[101],"it":[102,127],"handle":[104],"permutation-invariant":[105],"inputs":[106],"while":[107],"capturing":[108],"interactions":[109],"between":[110],"instances":[111],"within":[112],"each":[113],"bag.":[114],"The":[115,151],"model":[116],"is":[117],"conditioned":[118],"on":[119,140,174],"both":[120],"class":[121],"labels":[122],"input":[124],"scale,":[125],"allowing":[126],"generate":[129],"coherent":[130],"semantically":[132],"consistent":[133],"sets":[134],"representations.":[136],"We":[137],"evaluate":[138],"SetFlow":[139],"large-scale":[142],"mammography":[143],"benchmark":[144],"using":[145],"state-of-the-art":[147],"MIL-PF":[148],"classification":[149],"pipeline.":[150],"generated":[152],"samples":[153],"are":[154],"shown":[155],"closely":[157],"match":[158],"original":[160],"distribution":[162],"even":[164],"improve":[165],"downstream":[166],"when":[168],"used":[169],"for":[170,188],"augmentation.":[171],"Furthermore,":[172],"training":[173],"synthetic":[175],"alone":[177],"shows":[178],"competitive":[179],"results,":[180],"demonstrating":[181],"effectiveness":[183],"representation-space":[185],"modeling":[187],"data-scarce":[189],"privacy-sensitive":[191],"tasks.":[192]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-22T00:00:00"}