{"id":"https://openalex.org/W4290928007","doi":"https://doi.org/10.1145/3534678.3539153","title":"A Fully Differentiable Set Autoencoder","display_name":"A Fully Differentiable Set Autoencoder","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290928007","doi":"https://doi.org/10.1145/3534678.3539153"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539153","doi":"https://doi.org/10.1145/3534678.3539153","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539153","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539153","source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539153","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055447150","display_name":"Nikita Janakarajan","orcid":"https://orcid.org/0000-0001-7886-8385","observed_orcids":["https://orcid.org/0000-0001-7886-8385"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nikita Janakarajan","raw_affiliation_strings":["IBM Research Europe, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe, ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002562002","display_name":"Jannis Born","orcid":"https://orcid.org/0000-0001-8307-5670","observed_orcids":["https://orcid.org/0000-0001-8307-5670"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jannis Born","raw_affiliation_strings":["IBM Research Europe, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe, ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005561269","display_name":"Matteo Manica","orcid":"https://orcid.org/0000-0002-8872-0269","observed_orcids":["https://orcid.org/0000-0002-8872-0269"]},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matteo Manica","raw_affiliation_strings":["IBM Research Europe, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3229,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61477534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3061","last_page":"3071"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13899999856948853,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13899999856948853,"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/T10320","display_name":"Neural Networks and Applications","score":0.1331000030040741,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.07329999655485153,"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/permutation-invariance","display_name":"permutation invariance","score":0.8360000252723694},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.6679999828338623},{"id":"https://openalex.org/keywords/self-supervised-representation-learning","display_name":"self-supervised representation learning","score":0.7419999837875366},{"id":"https://openalex.org/keywords/differentiable-loss","display_name":"differentiable loss","score":0.36899998784065247},{"id":"https://openalex.org/keywords/bijective-mapping","display_name":"bijective mapping","score":0.574999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752507328987122},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6603820323944092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514864325523376},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5355510711669922},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5202816128730774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5089128017425537},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5019328594207764},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4688723385334015},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4182675778865814},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4121403098106384},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4096730053424835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4065527021884918},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37498289346694946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09861859679222107},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3534678.3539153","doi":"https://doi.org/10.1145/3534678.3539153","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539153","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539153","source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/570282","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/570282","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.3929/ethz-b-000570282","doi":"https://doi.org/10.3929/ethz-b-000570282","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000570282","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Other"}],"best_oa_location":{"id":"doi:10.1145/3534678.3539153","doi":"https://doi.org/10.1145/3534678.3539153","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539153","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539153","source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4290928007.pdf","grobid_xml":"https://content.openalex.org/works/W4290928007.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2068115726","https://openalex.org/W2121029939","https://openalex.org/W2747329762","https://openalex.org/W2805072236","https://openalex.org/W2912555327","https://openalex.org/W2916688788","https://openalex.org/W2990344448","https://openalex.org/W3034940913","https://openalex.org/W3098068064","https://openalex.org/W3133523400","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W4417152146","https://openalex.org/W3131923610","https://openalex.org/W2950224092","https://openalex.org/W2963764569","https://openalex.org/W4413318200","https://openalex.org/W4312116675","https://openalex.org/W3153588486","https://openalex.org/W3009411434","https://openalex.org/W7100762022","https://openalex.org/W3201639558"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"can":[2,98],"leverage":[3],"self-supervision":[4],"to":[5,17,50,64,89,122,158,181],"learn":[6,90,182],"integrated":[7],"representations":[8],"across":[9],"multiple":[10,52],"data":[11,24,53,69,81],"modalities.":[12],"This":[13],"makes":[14],"them":[15],"suitable":[16],"uncover":[18],"complex":[19],"relationships":[20],"between":[21,162],"vastly":[22],"different":[23],"types,":[25],"thus":[26],"lowering":[27],"the":[28,113,144,163,166,169,178,193],"dependency":[29],"on":[30,192,206],"labor-intensive":[31],"feature":[32],"engineering":[33],"methods.":[34],"Leveraging":[35],"deep":[36],"representation":[37,96,185],"learning,":[38],"we":[39,77,137],"propose":[40],"a":[41,56,84,91,117,147,153,160,183],"generic,":[42],"robust":[43],"and":[44,58,72,86,132,168],"systematic":[45],"model":[46,130,179],"that":[47,97,111,142],"is":[48,202],"able":[49],"combine":[51],"modalities":[54],"in":[55,68,101],"permutation":[57,94,135],"modes-number-invariant":[59],"fashion,":[60],"both":[61],"fundamental":[62],"properties":[63],"properly":[65],"face":[66],"changes":[67],"type":[70],"content":[71],"availability.":[73],"To":[74],"this":[75],"end,":[76],"treat":[78],"each":[79],"multi-modal":[80],"sample":[82],"as":[83,119],"set":[85,118,171],"utilise":[87],"autoencoders":[88,123],"fixed":[92],"size,":[93],"invariant":[95],"be":[99],"used":[100],"any":[102],"decision":[103],"making":[104],"process.":[105],"We":[106,176],"build":[107],"upon":[108],"previous":[109],"work":[110],"demonstrates":[112],"feasibility":[114],"of":[115,146,165,195],"presenting":[116],"an":[120,139],"input":[121,167],"through":[124],"content-based":[125],"attention":[126],"mechanisms.":[127],"However,":[128],"since":[129],"inputs":[131],"outputs":[133],"are":[134],"invariant,":[136],"develop":[138],"end-to-end":[140],"architecture":[141],"approximates":[143],"solution":[145],"linear":[148],"sum":[149],"assignment":[150],"problem,":[151,157],"i.e.,":[152],"minimum-cost":[154],"bijective":[155],"mapping":[156],"ensure":[159],"match":[161],"elements":[164],"output":[170],"for":[172],"effective":[173],"loss":[174],"calculation.":[175],"demonstrate":[177],"capability":[180],"combined":[184],"while":[186],"preserving":[187],"individual":[188],"mode":[189],"characteristics":[190],"focusing":[191],"task":[194],"reconstructing":[196],"multi-omic":[197],"cancer":[198],"data.":[199],"The":[200],"code":[201],"made":[203],"publicly":[204],"available":[205],"Github":[207],"https://github.com/PaccMann/fdsa":[208],").":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-08-13T00:00:00"}