{"id":"https://openalex.org/W2938319984","doi":null,"title":"Discretize and Conquer: Scalable Agglomerative Clustering in Hamming Space","display_name":"Discretize and Conquer: Scalable Agglomerative Clustering in Hamming Space","publication_year":2019,"publication_date":"2019-01-11","ids":{"openalex":"https://openalex.org/W2938319984","mag":"2938319984"},"language":"en","primary_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/14341","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/14341","pdf_url":"http://hdl.handle.net/10012/14341","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10012/14341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Soheil Soltani","orcid":"https://orcid.org/0000-0002-7223-8136","observed_orcids":["https://orcid.org/0000-0002-7223-8136"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Soheil Soltani","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7223-8136","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":true,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9970999956130981,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9970999956130981,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/agglomerative-hierarchical-clustering","display_name":"agglomerative clustering","score":0.9539999961853027},{"id":"https://openalex.org/keywords/hamming-space","display_name":"Hamming space","score":0.8489999771118164},{"id":"https://openalex.org/keywords/binary-data","display_name":"binary data","score":0.6859999895095825},{"id":"https://openalex.org/keywords/scalable-clustering","display_name":"scalable clustering","score":0.7200000286102295},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.5860000252723694},{"id":"https://openalex.org/keywords/binary-hashing","display_name":"binary hashing","score":0.4650000035762787},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"nearest neighbor search","score":0.6449999809265137},{"id":"https://openalex.org/keywords/binary-codes","display_name":"binary codes","score":0.4440000057220459},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.5239999890327454},{"id":"https://openalex.org/keywords/similarity-search","display_name":"similarity search","score":0.328000009059906},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.375},{"id":"https://openalex.org/keywords/image-clustering","display_name":"image clustering","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.688817024230957},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5704652070999146},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5553010106086731},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5035120844841003},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4975757896900177},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.48820358514785767},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.4795927107334137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4555467665195465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4326602518558502},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42459675669670105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34577590227127075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3077816963195801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25674116611480713},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08033740520477295},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.05930149555206299},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/14341","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/14341","pdf_url":"http://hdl.handle.net/10012/14341","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master Thesis"},{"id":"mag:2938319984","doi":null,"is_oa":false,"landing_page_url":"https://uwspace.uwaterloo.ca/bitstream/10012/14341/1/Soltani_Soheil.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/14341","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/14341","pdf_url":"http://hdl.handle.net/10012/14341","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2938319984.pdf","grobid_xml":"https://content.openalex.org/works/W2938319984.grobid-xml"},"referenced_works_count":138,"referenced_works":["https://openalex.org/W90763689","https://openalex.org/W171785542","https://openalex.org/W195533127","https://openalex.org/W255433357","https://openalex.org/W269095843","https://openalex.org/W372789814","https://openalex.org/W1481653166","https://openalex.org/W1487583988","https://openalex.org/W1492327544","https://openalex.org/W1492839618","https://openalex.org/W1500807780","https://openalex.org/W1510029899","https://openalex.org/W1529320607","https://openalex.org/W1531910981","https://openalex.org/W1548431126","https://openalex.org/W1560541823","https://openalex.org/W1566114229","https://openalex.org/W1566135517","https://openalex.org/W1571401318","https://openalex.org/W1608792154","https://openalex.org/W1633659671","https://openalex.org/W1651093245","https://openalex.org/W1660133578","https://openalex.org/W1673310716","https://openalex.org/W1676119944","https://openalex.org/W1742512077","https://openalex.org/W1765998458","https://openalex.org/W1769669223","https://openalex.org/W1849277567","https://openalex.org/W1870625491","https://openalex.org/W1907458443","https://openalex.org/W1946550961","https://openalex.org/W1964414401","https://openalex.org/W1967368946","https://openalex.org/W1974647172","https://openalex.org/W1975900269","https://openalex.org/W1979931291","https://openalex.org/W1986007546","https://openalex.org/W1990368529","https://openalex.org/W1990517717","https://openalex.org/W1993670676","https://openalex.org/W2001141328","https://openalex.org/W2011420344","https://openalex.org/W2011430131","https://openalex.org/W2012833704","https://openalex.org/W2016381774","https://openalex.org/W2020365462","https://openalex.org/W2029205712","https://openalex.org/W2032279931","https://openalex.org/W2033403400","https://openalex.org/W2034331023","https://openalex.org/W2034900106","https://openalex.org/W2035890032","https://openalex.org/W2038276547","https://openalex.org/W2044195942","https://openalex.org/W2049631158","https://openalex.org/W2049633694","https://openalex.org/W2053186076","https://openalex.org/W2054638878","https://openalex.org/W2057712948","https://openalex.org/W2064520788","https://openalex.org/W2064980127","https://openalex.org/W2067642075","https://openalex.org/W2073308541","https://openalex.org/W2075500727","https://openalex.org/W2080051862","https://openalex.org/W2082929085","https://openalex.org/W2099068394","https://openalex.org/W2099443716","https://openalex.org/W2103633133","https://openalex.org/W2105354819","https://openalex.org/W2108503327","https://openalex.org/W2109722477","https://openalex.org/W2112148214","https://openalex.org/W2112796928","https://openalex.org/W2115845039","https://openalex.org/W2116762767","https://openalex.org/W2117920736","https://openalex.org/W2119667497","https://openalex.org/W2120468118","https://openalex.org/W2120636855","https://openalex.org/W2121947440","https://openalex.org/W2121949863","https://openalex.org/W2122196799","https://openalex.org/W2122457239","https://openalex.org/W2124509324","https://openalex.org/W2124812588","https://openalex.org/W2124957865","https://openalex.org/W2125027820","https://openalex.org/W2126337883","https://openalex.org/W2126626732","https://openalex.org/W2127211325","https://openalex.org/W2129275750","https://openalex.org/W2129638195","https://openalex.org/W2130325614","https://openalex.org/W2134312057","https://openalex.org/W2134648451","https://openalex.org/W2135001774","https://openalex.org/W2139850885","https://openalex.org/W2140363548","https://openalex.org/W2141362318","https://openalex.org/W2145096794","https://openalex.org/W2145962650","https://openalex.org/W2148495331","https://openalex.org/W2148554573","https://openalex.org/W2148675068","https://openalex.org/W2149230623","https://openalex.org/W2150593711","https://openalex.org/W2155465666","https://openalex.org/W2155541015","https://openalex.org/W2156718197","https://openalex.org/W2156838815","https://openalex.org/W2157169955","https://openalex.org/W2158312129","https://openalex.org/W2158703410","https://openalex.org/W2160642098","https://openalex.org/W2165213086","https://openalex.org/W2165874743","https://openalex.org/W2166933393","https://openalex.org/W2167853719","https://openalex.org/W2169507824","https://openalex.org/W2184038071","https://openalex.org/W2221852422","https://openalex.org/W2251864938","https://openalex.org/W2293597654","https://openalex.org/W2296616510","https://openalex.org/W2302536180","https://openalex.org/W2308071406","https://openalex.org/W2332521218","https://openalex.org/W2403924105","https://openalex.org/W2524365899","https://openalex.org/W2612150260","https://openalex.org/W2735551594","https://openalex.org/W2963542991","https://openalex.org/W2999729612","https://openalex.org/W3099839986","https://openalex.org/W3217167116","https://openalex.org/W4236362309"],"related_works":["https://openalex.org/W2007299667","https://openalex.org/W2383586310","https://openalex.org/W7098891564","https://openalex.org/W7100215752","https://openalex.org/W1554157714","https://openalex.org/W3169046719","https://openalex.org/W7095117186","https://openalex.org/W2570542106","https://openalex.org/W2030076336","https://openalex.org/W2396589505"],"abstract_inverted_index":{"Clustering":[0,500,623],"is":[1,20,52,60,129,144,315,365,386,496,504,528,618,626,690],"one":[2,746],"of":[3,50,114,136,152,158,174,194,211,229,237,273,277,289,319,362,374,383,405,443,447,457,476,486,510,531,546,573,576,593,615,640,673,751],"the":[4,18,32,45,88,112,130,142,172,175,181,212,217,227,254,324,332,355,372,378,416,422,434,445,458,487,497,507,524,557,571,591,635,643,659,663,670,681,720],"most":[5,456,488],"fundamental":[6],"tasks":[7,205],"in":[8,31,39,104,138,209,252,295,306,345,354,366,377,493,553,561,599,652,656,760],"many":[9,473],"machine":[10],"learning":[11],"and":[12,47,75,97,106,156,164,190,216,243,279,299,467,490,556,580,596,637,654,705,715,741,759],"information":[13],"retrieval":[14],"applications.":[15,140],"Roughly":[16],"speaking,":[17],"goal":[19,382],"to":[21,77,82,132,199,223,329,387,400,440,482,515,519,582,628,658,678,733],"partition":[22],"data":[23,89,238,559],"instances":[24,28,37,96,256,560],"such":[25,149,161,169,239,267,293,391,606,700,711],"that":[26,125,219,534,541,625,728],"similar":[27,95],"end":[29],"up":[30],"same":[33,333],"group":[34],"while":[35],"dissimilar":[36],"lie":[38],"different":[40,583],"groups.":[41,93],"Quite":[42],"surprisingly":[43],"though,":[44],"formal":[46],"rigorous":[48],"definition":[49],"clustering":[51,185,202,231,290,322,446,469,477,495,532,604,675,698,742,757],"not":[53,107],"at":[54,433,590],"all":[55,71],"clear":[56],"mainly":[57],"because":[58],"there":[59],"no":[61,188,567],"consensus":[62],"about":[63,87,570],"what":[64],"constitutes":[65],"a":[66,84,145,191,230,249,274,303,316,351,402,529,536,543,550,613],"cluster.":[67],"That":[68],"said,":[69],"across":[70],"disciplines,":[72],"from":[73,676],"mathematics":[74],"statistics":[76],"genetics,":[78],"people":[79],"frequently":[80],"try":[81],"get":[83],"first":[85],"intuition":[86],"through":[90],"identifying":[91],"meaningful":[92],"Finding":[94],"grouping":[98],"them":[99,577,743],"are":[100,187,221,257,461,578,718],"two":[101,419],"main":[102,182],"steps":[103],"clustering,":[105,298,337],"surprisingly,":[108],"both":[109,208,651],"have":[110,215],"been":[111,123,197,371],"subject":[113],"extensive":[115],"study":[116],"over":[117],"recent":[118],"decades.":[119],"\\n":[120,283,437,438,609],"\\nIt":[121],"has":[122,196,264,370,450],"shown":[124],"using":[126,429,736],"large":[127],"datasets":[128,449,710],"key":[131],"achieving":[133,763],"acceptable":[134],"levels":[135],"performance":[137,173],"data-driven":[139],"Today,":[141],"Internet":[143],"vast":[146],"resource":[147],"for":[148,168,308,685,723],"datasets,":[150,171],"each":[151,312,347],"which":[153,346,369,503,717],"contains":[154],"millions":[155],"billions":[157],"high-dimensional":[159,389],"items":[160,328],"as":[162,240,268,294,342,392,399,415,538,607,701,712],"images":[163],"text":[165],"documents.":[166],"However,":[167],"large-scale":[170,724],"employed":[176],"machine-learning":[177],"algorithm":[178,232],"quickly":[179,428],"becomes":[180],"bottleneck.":[183],"Conventional":[184],"algorithms":[186,492,565,605,617,645,667,699,740],"exception,":[189],"great":[192],"deal":[193],"effort":[195],"devoted":[198],"developing":[200],"scalable":[201],"algorithms.":[203,725],"\\nClustering":[204],"can":[206,233,326,339,425,479,646,668,747],"vary":[207],"terms":[210],"input":[213,228,255],"they":[214,220],"output":[218],"expected":[222],"generate.":[224],"For":[225],"instance,":[226],"hold":[234],"various":[235],"types":[236,442,475],"continuous":[241],"numerical,":[242],"categorical":[244],"types.":[245],"This":[246],"thesis":[247],"on":[248,506,708],"particular":[250],"setting;":[251],"it,":[253],"represented":[258,341],"with":[259,287,331,394,464,601,630,695,744],"binary":[260,291,317,343,363,367,384,396,448,483,631,641,734,738],"strings.":[261],"Binary":[262],"representation":[263,318],"several":[265,749],"advantages":[266,588],"storage":[269,597],"efficiency,":[270],"simplicity,":[271],"lack":[272],"numerical-data-like":[275],"concept":[276],"noise,":[278],"being":[280,512],"naturally":[281],"normalized.":[282],"\\nThe":[284],"literature":[285],"abounds":[286],"applications":[288],"data,":[292,444],"marketing,":[296],"document":[297,336,356],"image":[300],"clustering.":[301],"As":[302,523],"more-concrete":[304],"example,":[305],"marketing":[307],"an":[309],"online":[310],"store,":[311],"customer's":[313],"basket":[314],"items.":[320],"By":[321,633],"customers,":[323],"store":[325],"recommend":[327],"customers":[330],"interests.":[334],"In":[335],"documents":[338],"be":[340,426,480,692],"codes":[344,364,408,420],"element":[348],"indicates":[349],"whether":[350],"word":[352],"exists":[353],"or":[357],"not.":[358],"Another":[359],"notable":[360],"application":[361],"hashing,":[368],"topic":[373],"significant":[375,648],"research":[376,453],"last":[379],"decade.":[380],"The":[381,687],"hashing":[385,739],"encode":[388],"items,":[390],"images,":[393],"compact":[395],"strings":[397],"so":[398],"preserve":[401],"given":[403],"notion":[404],"similarity.":[406],"Such":[407,564],"enable":[409],"extremely":[410],"fast":[411],"nearest":[412],"neighbour":[413],"searches,":[414],"distance":[417],"between":[418],"(often":[421],"Hamming":[423],"distance)":[424],"computed":[427],"bit-wise":[430],"operations":[431],"implemented":[432],"hardware":[435],"level.":[436],"Similar":[439],"other":[441,474,602,696],"witnessed":[451],"considerable":[452],"recently.":[454],"Unfortunately,":[455],"existing":[459,660,737],"approaches":[460],"only":[462],"concerned":[463],"devising":[465],"density":[466],"centroid-based":[468],"algorithms,":[470],"even":[471,764],"though":[472],"techniques":[478],"applied":[481],"data.":[484,632],"One":[485],"popular":[489,603],"intuitive":[491],"connectivity-based":[494],"Hierarchical":[498],"Agglomerative":[499,622],"(HAC)":[501],"algorithm,":[502],"based":[505],"core":[508],"idea":[509],"objects":[511,517,520],"more":[513],"related":[514],"nearby":[516],"than":[518],"farther":[521],"away.":[522],"name":[525],"suggests,":[526],"HAC":[527,616],"family":[530,614],"methods":[533],"return":[535],"dendrogram":[537],"their":[539,554,562],"output:":[540],"is,":[542],"hierarchical":[544,674],"tree":[545],"domain":[547],"subsets,":[548],"having":[549],"singleton":[551],"instance":[552],"leaves":[555],"whole":[558],"root.":[563],"need":[566],"prior":[568],"knowledge":[569],"number":[572],"clusters.":[574],"Most":[575],"deterministic":[579],"applicable":[581],"cluster":[584],"shapes,":[585],"but":[586],"these":[587],"come":[589],"price":[592],"high":[594],"computational":[595,671],"costs":[598],"comparison":[600,657],"k-means.":[608],"\\nIn":[610],"this":[611],"thesis,":[612],"proposed,":[619],"called":[620],"Discretized":[621],"(DAC),":[624],"designed":[627],"work":[629],"leveraging":[634],"discretized":[636],"bounded":[638],"nature":[639],"representation,":[642],"proposed":[644,688],"achieve":[647,748],"speedup":[649],"factors":[650],"theory":[653],"practice,":[655],"solutions.":[661],"From":[662],"theoretical":[664],"perspective,":[665],"DAC":[666],"reduce":[669],"cost":[672],"cubic":[677],"quadratic,":[679],"matching":[680],"known":[682],"lower":[683],"bounds":[684],"HAC.":[686],"approach":[689],"also":[691],"empirically":[693],"compared":[694],"well-known":[697,709],"k-means,":[702],"DBSCAN,":[703],"average,":[704],"complete-linkage":[706],"HAC,":[707],"TEXMEX,":[713],"CIFAR-10":[714],"MNIST,":[716],"among":[719],"standard":[721],"benchmarks":[722],"Results":[726],"indicate":[727],"by":[729],"mapping":[730],"real":[731],"points":[732],"vectors":[735],"DAC,":[745],"orders":[750],"magnitude":[752],"speed":[753],"without":[754],"losing":[755],"much":[756],"quality,":[758],"some":[761],"cases,":[762],"more.":[765]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-04-25T00:00:00"}