{"id":"https://openalex.org/W6884686600","doi":"https://doi.org/10.11588/heidok.00033875","title":"Discovering structure without labels","display_name":"Discovering structure without labels","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6884686600","doi":"https://doi.org/10.11588/heidok.00033875"},"language":"en","primary_location":{"id":"pmh:oai:archiv.ub.uni-heidelberg.de:33875","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402333","display_name":"heiDOK (Heidelberg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I223822909","host_organization_name":"Heidelberg University","host_organization_lineage":["https://openalex.org/I223822909"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Damrich, Sebastian","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Damrich, Sebastian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23993002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.48100000619888306,"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/T10799","display_name":"Data Visualization and Analytics","score":0.48100000619888306,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.15000000596046448,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.07429999858140945,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7287999987602234},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5174000263214111},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4993000030517578},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49399998784065247},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4810999929904938},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47040000557899475},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/complete-linkage-clustering","display_name":"Complete-linkage clustering","score":0.44269999861717224},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4309000074863434},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41029998660087585}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7287999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.532800018787384},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5174000263214111},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4745999872684479},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C23822008","wikidata":"https://www.wikidata.org/wiki/Q5156437","display_name":"Complete-linkage clustering","level":5,"score":0.44269999861717224},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38909998536109924},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.3749000132083893},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C13743678","wikidata":"https://www.wikidata.org/wiki/Q240464","display_name":"Minimum spanning tree","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C2778626561","wikidata":"https://www.wikidata.org/wiki/Q6086067","display_name":"Isomap","level":4,"score":0.2565000057220459},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:archiv.ub.uni-heidelberg.de:33875","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402333","display_name":"heiDOK (Heidelberg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I223822909","host_organization_name":"Heidelberg University","host_organization_lineage":["https://openalex.org/I223822909"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},{"id":"doi:10.11588/heidok.00033875","is_oa":true,"landing_page_url":"https://doi.org/10.11588/heidok.00033875","pdf_url":null,"source":{"id":"https://openalex.org/S7407051545","display_name":"University Library Heidelberg","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:archiv.ub.uni-heidelberg.de:33875","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402333","display_name":"heiDOK (Heidelberg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I223822909","host_organization_name":"Heidelberg University","host_organization_lineage":["https://openalex.org/I223822909"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,216],"scarcity":[1],"of":[2,8,25,39,70,78,83,143,273,296,308,329,336],"labels":[3],"combined":[4],"with":[5,338],"an":[6],"abundance":[7],"data":[9,64],"makes":[10],"unsupervised":[11,40],"learning":[12],"more":[13,253,288,291,303],"attractive":[14],"than":[15,255],"ever.":[16],"Without":[17],"annotations,":[18],"inductive":[19],"biases":[20],"must":[21],"guide":[22],"the":[23,26,31,52,76,81,103,131,141,156,174,210,225,265,294,297,309,314],"identification":[24],"most":[27],"salient":[28],"structure":[29,307],"in":[30,120,129,169],"data.":[32,310],"This":[33,160],"thesis":[34,46],"contributes":[35],"to":[36,74,85,102,118,164,178,184,196,209,241,259,290,302],"two":[37,49],"aspects":[38],"learning:":[41],"clustering":[42,60,119],"and":[43,72,80,137,146,234,280,305,320],"dimensionality":[44,126],"reduction.
\\n
\\nThe":[45],"falls":[47],"into":[48],"parts.":[50],"In":[51],"first":[53],"part,":[54],"we":[55,187,204,247,269,312],"introduce":[56],"Mod":[57],"Shift,":[58],"a":[59,67,111,220,245,271],"method":[61],"for":[62,334],"point":[63],"that":[65,189,249,326],"uses":[66],"distance-based":[68],"notion":[69],"attraction":[71,261,266,289],"repulsion":[73,292],"determine":[75],"number":[77],"clusters":[79,93],"assignment":[82],"points":[84,90],"clusters.":[86],"It":[87,152],"iteratively":[88],"moves":[89],"towards":[91],"crisp":[92,181],"like":[94],"Mean":[95],"Shift":[96],"but":[97],"also":[98],"has":[99,238],"close":[100],"ties":[101],"Multicut":[104],"problem":[105],"via":[106],"its":[107,148,197,206],"loss":[108,150,227],"function.":[109,151],"As":[110,244],"result,":[112,246],"it":[113],"connects":[114],"signed":[115],"graph":[116],"partitioning":[117],"Euclidean":[121],"space.
\\n
\\nThe":[122],"second":[123],"part":[124],"treats":[125],"reduction":[127],"and,":[128],"particular,":[130],"prominent":[132],"neighbor":[133,274,318],"embedding":[134,275,298],"methods":[135],"UMAP":[136,170,250],"t-SNE.":[138,215,243],"We":[139,324],"analyze":[140],"details":[142],"UMAP's":[144,190,201],"implementation":[145],"find":[147,188],"actual":[149,202],"differs":[153],"drastically":[154],"from":[155,287,299],"one":[157],"usually":[158],"stated.":[159],"discrepancy":[161],"allows":[162],"us":[163],"explain":[165,248],"some":[166],"typical":[167],"artifacts":[168],"plots,":[171],"such":[172],"as":[173,283],"dataset":[175],"size-dependent":[176],"tendency":[177],"produce":[179],"overly":[180],"substructures.":[182],"Contrary":[183],"existing":[185],"belief,":[186],"high-dimensional":[191],"similarities":[192],"are":[193],"not":[194],"critical":[195],"success.":[198],"
\\n
\\nBased":[199],"on":[200],"loss,":[203],"describe":[205],"precise":[207],"connection":[208],"other":[211],"state-of-the-art":[212],"visualization":[213],"method,":[214],"key":[217],"insight":[218],"is":[219],"new,":[221],"exact":[222],"relation":[223],"between":[224,262,316],"contrastive":[226,317,322,330],"functions":[228],"negative":[229],"sampling,":[230],"employed":[231],"by":[232],"UMAP,":[233],"noise-contrastive":[235],"estimation,":[236],"which":[237],"been":[239],"used":[240],"approximate":[242],"embeddings":[251,319],"appear":[252],"compact":[254],"t-SNE":[256],"plots":[257],"due":[258],"increased":[260],"neighbors.":[263],"Varying":[264],"strength":[267],"further,":[268],"obtain":[270],"spectrum":[272],"methods,":[276],"encompassing":[277],"both":[278,335],"UMAP-":[279],"t-SNE-like":[281],"versions":[282],"special":[284],"cases.":[285],"Moving":[286],"shifts":[293],"focus":[295],"continuous,":[300],"global":[301],"discrete":[304],"local":[306],"Finally,":[311],"emphasize":[313],"link":[315],"self-supervised":[321],"learning.":[323],"show":[325],"different":[327],"flavors":[328],"losses":[331],"can":[332],"work":[333],"them":[337],"few":[339],"noise":[340],"samples.":[341]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}