{"id":"https://openalex.org/W4304080190","doi":"https://doi.org/10.1145/3503161.3547798","title":"On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning","display_name":"On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080190","doi":"https://doi.org/10.1145/3503161.3547798"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547798","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5105369758","display_name":"Muhammad Umer Anwaar","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Muhammad Umer Anwaar","raw_affiliation_strings":["Unite Network SE & Technical University of Munich, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unite Network SE & Technical University of Munich, Leipzig, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042360856","display_name":"Zhihui Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhihui Pan","raw_affiliation_strings":["Unite Network SE & Technical University of Munich, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unite Network SE & Technical University of Munich, Leipzig, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055847035","display_name":"Martin Kleinsteuber","orcid":"https://orcid.org/0000-0002-4323-9260"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Kleinsteuber","raw_affiliation_strings":["Unite Network SE & Technical University of Munich, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unite Network SE & Technical University of Munich, Leipzig, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105369758"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.4559,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84250132,"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":"4645","last_page":"4654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.968999981880188,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7069317102432251},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6329909563064575},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5197762846946716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157449841499329},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5013949871063232},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4805598556995392},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48027801513671875},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.44872987270355225},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4450932741165161},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44265884160995483},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.43452900648117065},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.399326354265213},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3472471833229065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3261922001838684},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2120911180973053},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.137128084897995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069317102432251},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6329909563064575},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5197762846946716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157449841499329},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5013949871063232},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4805598556995392},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48027801513671875},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.44872987270355225},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4450932741165161},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44265884160995483},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.43452900648117065},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.399326354265213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3472471833229065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3261922001838684},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2120911180973053},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.137128084897995},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547798","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W64813323","https://openalex.org/W1501418839","https://openalex.org/W1599238028","https://openalex.org/W1834627138","https://openalex.org/W1849277567","https://openalex.org/W1948251820","https://openalex.org/W2010132303","https://openalex.org/W2040171755","https://openalex.org/W2052293776","https://openalex.org/W2098411764","https://openalex.org/W2157423479","https://openalex.org/W2160160833","https://openalex.org/W2250539671","https://openalex.org/W2400717490","https://openalex.org/W2441043183","https://openalex.org/W2493916176","https://openalex.org/W2736809457","https://openalex.org/W2768346313","https://openalex.org/W2889167066","https://openalex.org/W2905544595","https://openalex.org/W2912500072","https://openalex.org/W2913668833","https://openalex.org/W2963336393","https://openalex.org/W2963499153","https://openalex.org/W2986385672","https://openalex.org/W3102100346","https://openalex.org/W3109684201","https://openalex.org/W3119510203","https://openalex.org/W3157598734","https://openalex.org/W3164731060"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2075445622","https://openalex.org/W2009836834","https://openalex.org/W2914691919","https://openalex.org/W4297851895"],"abstract_inverted_index":{"Humans":[0],"are":[1,199],"able":[2],"to":[3,20,102,110],"identify":[4],"and":[5,28,141,156,171],"categorize":[6],"novel":[7,37,57],"compositions":[8,38,64,94],"of":[9,23,56,83,92,138,178],"known":[10],"concepts.":[11],"The":[12],"task":[13,192],"in":[14,30,108,161],"Compositional":[15,72],"Zero-Shot":[16],"learning":[17,79,154],"(CZSL)":[18],"is":[19,107,115],"learn":[21,135],"composition":[22],"primitive":[24,85],"concepts,":[25],"i.e.":[26,59],"objects":[27],"states,":[29],"such":[31],"a":[32,71,136,145,151,158],"way":[33],"that":[34,193],"even":[35],"their":[36,93],"can":[39],"be":[40],"zero-shot":[41],"classied.":[42],"In":[43],"this":[44,162],"work,":[45],"we":[46],"do":[47],"not":[48],"assume":[49],"any":[50],"prior":[51],"knowledge":[52],"on":[53,181],"the":[54,66,80,84,139,176,194],"feasibility":[55,91],"compositions,":[58],"open-world":[60],"setting,":[61],"where":[62],"infeasible":[63],"dominate":[65],"search":[67],"space.":[68,148],"We":[69,134,174,185],"propose":[70],"Variational":[73],"Graph":[74],"Autoencoder":[75],"(CVGAE)":[76],"approach":[77,155,180],"for":[78,120,202],"variational":[81],"embeddings":[82,143],"concepts":[86],"(nodes)":[87],"as":[88,90],"well":[89],"(via":[95],"edges).":[96],"Such":[97],"modelling":[98],"makes":[99],"CVGAE":[100,129,149,198],"scalable":[101],"real-world":[103],"application":[104],"scenarios.":[105],"This":[106],"contrast":[109],"SOTA":[111],"method,":[112],"CGE,":[113],"which":[114],"computationally":[116],"very":[117],"expensive.":[118],"e.g.":[119],"benchmark":[121,183],"C-GQA":[122],"dataset,":[123],"CGE":[124],"requires":[125,130],"3.94\u00d710^5":[126],"nodes,":[127],"whereas":[128],"only":[131],"1323":[132],"nodes.":[133],"mapping":[137],"graph":[140,170],"image":[142,172,190],"onto":[144],"common":[146],"embedding":[147],"adopts":[150],"deep":[152],"metric":[153,160],"learns":[157],"similarity":[159],"space":[163],"via":[164,188],"bi-directional":[165],"contrastive":[166],"loss":[167],"between":[168],"projected":[169],"embeddings.":[173],"validate":[175],"eectiveness":[177],"our":[179],"three":[182],"datasets.":[184],"also":[186],"demonstrate":[187],"an":[189],"retrieval":[191],"representations":[195],"learnt":[196],"by":[197],"better":[200],"suited":[201],"compositional":[203],"generalization.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}