{"id":"https://openalex.org/W4313438671","doi":"https://doi.org/10.1515/9783110785944-004","title":"4 Structured Data","display_name":"4 Structured Data","publication_year":2022,"publication_date":"2022-12-19","ids":{"openalex":"https://openalex.org/W4313438671","doi":"https://doi.org/10.1515/9783110785944-004"},"language":"en","primary_location":{"id":"doi:10.1515/9783110785944-004","is_oa":true,"landing_page_url":"https://doi.org/10.1515/9783110785944-004","pdf_url":"https://www.degruyter.com/document/doi/10.1515/9783110785944-004/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fundamentals","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.degruyter.com/document/doi/10.1515/9783110785944-004/pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029876355","display_name":"Nico Piatkowski","orcid":"https://orcid.org/0000-0002-6334-8042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nico Piatkowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065328227","display_name":"Katharina Morik","orcid":"https://orcid.org/0000-0003-1153-5986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katharina Morik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009569829","display_name":"Nils M. Kriege","orcid":"https://orcid.org/0000-0003-2645-947X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nils Kriege","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111798651","display_name":"Christopher G. Morris","orcid":"https://orcid.org/0000-0002-3863-7504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher Morris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002742256","display_name":"Matthias Fey","orcid":"https://orcid.org/0000-0002-5727-0701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Fey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004108638","display_name":"Frank Weichert","orcid":"https://orcid.org/0000-0002-2530-8197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Weichert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035605605","display_name":"Nico Bertram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nico Bertram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035566443","display_name":"Jonas Ellert","orcid":"https://orcid.org/0000-0003-3305-6185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonas Ellert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024743438","display_name":"Johannes Fischer","orcid":"https://orcid.org/0000-0002-1886-6633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johannes Fischer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005777739","display_name":"Lukas Pfahler","orcid":"https://orcid.org/0000-0003-4012-4502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas Pfahler","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47445972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9703999757766724,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9702000021934509,"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/computer-science","display_name":"Computer science","score":0.60788893699646},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5717593431472778},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.5610402822494507},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44909510016441345},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43868303298950195},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4312346875667572},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4231288433074951},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.4224443733692169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4145428538322449},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.41290345788002014},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4114542603492737},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3145010769367218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.60788893699646},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5717593431472778},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5610402822494507},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44909510016441345},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43868303298950195},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4312346875667572},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4231288433074951},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.4224443733692169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4145428538322449},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.41290345788002014},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4114542603492737},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3145010769367218},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C74902906","wikidata":"https://www.wikidata.org/wiki/Q1190858","display_name":"Radiative transfer","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1515/9783110785944-004","is_oa":true,"landing_page_url":"https://doi.org/10.1515/9783110785944-004","pdf_url":"https://www.degruyter.com/document/doi/10.1515/9783110785944-004/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fundamentals","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1515/9783110785944-004","is_oa":true,"landing_page_url":"https://doi.org/10.1515/9783110785944-004","pdf_url":"https://www.degruyter.com/document/doi/10.1515/9783110785944-004/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fundamentals","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313438671.pdf","grobid_xml":"https://content.openalex.org/works/W4313438671.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4239315977","https://openalex.org/W2153421756","https://openalex.org/W2077818434","https://openalex.org/W2054489697","https://openalex.org/W2361081803","https://openalex.org/W2036241269","https://openalex.org/W2106257677","https://openalex.org/W2964321162","https://openalex.org/W4322716735","https://openalex.org/W2042907335"],"abstract_inverted_index":{"Parameter":[0],"sharing":[1,123],"is":[2,15,59,124,145,250,263,272,301,333,587,640,783,835,918,967,1058,1117],"a":[3,20,110,132,201,212,245,253,302,420,429,533,544,601,636,643,663,723,776,821,824,852,867,957,961,972,1040,1098,1120],"key":[4],"technique":[5],"in":[6,81,97,175,227,252,338,554,566,582,775,883,891,924,933,956,1025,1130],"various":[7],"state-of-the-art":[8],"machine":[9,181,339,503,983],"learning":[10,182,238,340,504,567,649,666,990],"approaches.":[11],"The":[12,179,331,800,1056],"underlying":[13,222,529],"idea":[14],"simple":[16],"yet":[17],"effective.":[18],"Given":[19],"highly":[21],"overparametrized":[22],"model":[23,73],"whose":[24,322],"input":[25,858],"data":[26,66,91,475,530],"obeys":[27],"some":[28,458],"repetitive":[29],"structure,":[30],"multiple":[31],"subsets":[32],"of":[33,46,64,88,134,151,220,293,314,355,392,423,433,452,527,546,564,571,600,625,632,646,653,660,701,710,740,762,797,812,828,880,894,912,926,978,1011,1090,1100,1108],"parameters":[34],"are":[35,155,328,364,914,1074],"tied":[36],"together.":[37],"On":[38,54],"the":[39,44,50,55,65,72,82,86,93,98,104,118,127,194,221,237,260,276,290,353,360,366,381,390,405,415,450,461,528,561,572,588,598,623,630,658,707,741,759,763,772,787,795,813,832,857,889,892,897,922,954,965,976,1008,1106],"one":[40,62,570],"hand,":[41,57],"this":[42,116,434,717,1071],"reduces":[43],"number":[45,624,796,893],"parameters,":[47],"which":[48,309,363,380,1064],"simplifies":[49],"corresponding":[51,180],"estimation":[52],"problem.":[53],"other":[56,446],"information":[58],"transferred":[60,125],"from":[61,211,379,749,1049],"part":[63,811],"space":[67,107,205],"to":[68,74,126,157,189,438,550,590,593,612,622,657,688,715,732,757,784,808,921,963,1006,1076],"another,":[69],"thus":[70],"allowing":[71],"learn":[75],"patterns":[76],"that":[77,120,206,259,267,428,487,574,617,639,695,850,992,1029,1082],"never":[78],"explicitly":[79],"occurred":[80],"training":[83,751,1087],"data.":[84,232,1069],"In":[85,115,494,596,691,713,820,905,1070],"context":[87],"resource":[89],"constrained":[90],"analysis,":[92],"primary":[94],"interest":[95],"lies":[96],"reduced":[99],"memory":[100],"requirements,":[101],"induced":[102],"by":[103,317,531,744,946],"lower":[105,112],"parameter":[106,122,204,261],"dimension":[108],"and":[109,224,266,285,346,396,404,440,466,481,515,539,584,648,670,837,873,936,998,1080,1088,1124],"presumably":[111],"sample":[113],"complexity.":[114],"contribution,":[117],"concept":[119],"underlies":[121],"spatio-temporal":[128,171],"domain.":[129],"More":[130],"precisely,":[131],"re-parametrization":[133,223],"undirected":[135],"probabilistic":[136,198,208],"graphical":[137],"models,":[138,1037],"known":[139],"as":[140,477,929,1067],"Markov":[141],"Random":[142,296],"Fields":[143,297],"(MRFs)":[144],"proposed":[146,501],"for":[147,169,275,305,335,375,402,469,502,642,668,683,725,770,899,975,1086,1112],"non-stationary":[148],"time":[149],"series":[150],"finite":[152],"length.":[153],"MRFs":[154],"equivalent":[156],"deep":[158,665],"latent":[159],"variable":[160],"models":[161,172,183,199,284,288,1111],"[568]":[162],"but":[163],"obey":[164],"an":[165,806,987,1061],"easier-to-interpret":[166],"structure.":[167],"Data":[168],"such":[170,476,568],"arises":[173],"naturally":[174],"distributed":[176,254],"sensor":[177,195,246,270,286],"networks.":[178,349],"are,":[184],"however,":[185],"far":[186,577],"too":[187],"large":[188,594,733,777],"be":[190,241,944,1128],"processed":[191],"directly":[192,210,243,385],"at":[193,937,953],"level.":[196],"Re-parametrized":[197],"exhibit":[200],"very":[202],"sparse":[203],"facilitates":[207],"inference":[209],"compressed":[213,294],"model.":[214],"This":[215,350,651,917,1115],"section":[216],"studies":[217],"different":[218,547,556,934,938],"variants":[219],"compares":[225],"them":[226,592],"numerical":[228],"experiments":[229],"on":[230,359,414,449,460,505,512,543,606,699,982,1054,1119],"benchmark":[231],"Furthermore,":[233,678,1093],"we":[234,388,444,456,628,679,693,719,865,970,1021,1038,1065,1073,1083],"propose":[235,971],"how":[236],"procedure":[239],"can":[240,436,1084,1127],"embedded":[242],"into":[244,789,860,1060],"network:":[247],"proximal":[248],"optimization":[249,262],"applied":[251],"setting.":[255],"It":[256],"turns":[257],"out":[258],"purely":[264],"local":[265,810],"communication":[268],"between":[269,463,615,870],"nodes":[271,616],"required":[273],"only":[274],"gradient":[277],"computation.":[278],"Different":[279],"real-world":[280],"applications,":[281],"including":[282],"traffic":[283],"network":[287,675],"underpin":[289],"practical":[291],"relevance":[292],"Spatio-Temporal":[295],"(STRF).":[298],"TheWeisfeiler-Leman":[299],"method":[300,332],"classic":[303],"heuristic":[304,374],"graph":[306,344,347,356,369,376,408,513,557,685,743,788,814,859,1017,1068],"isomorphism":[307,377],"testing,":[308,378],"iteratively":[310],"encodes":[311],"vertex":[312,318,323],"neighborhoods":[313],"increasing":[315],"radius":[316],"colors.":[319],"Two":[320],"graphs":[321,403,506],"colors":[324],"do":[325],"not":[326,915],"match":[327],"called":[329],"non-isomorphic.":[330],"fundamental":[334],"recent":[336,495],"advances":[337],"with":[341,473,620,672,1043],"graphs,":[342],"e.g.,":[343],"kernels":[345,357,370,395,447,465,514],"neural":[348,467,521,535,674,686,730,1019],"contribution":[351,1116],"overviews":[352],"development":[354,659],"based":[358,413,448,511,698,981,1118],"Weisfeiler-Leman":[361,407,418,453],"algorithm,":[362,419],"among":[365],"most":[367,508],"successful":[368],"today.We":[371],"describe":[372],"theWeisfeiler-Leman":[373,398,424],"classicalWeisfeiler-Leman":[382],"subtree":[383],"kernel":[384,401,411],"follows.":[386],"Further,":[387],"summarize":[389],"theory":[391],"optimal":[393,399],"assignment":[394,400],"present":[397,720],"relatedWasserstein":[406],"kernel.We":[409],"discuss":[410,680],"functions":[412],"k":[416],"-dimensional":[417],"strict":[421],"generalization":[422],"heuristic.":[425],"We":[426,766,876,985,1001],"show":[427,694,878,1105],"local,":[430],"sparsity-aware":[431],"variant":[432],"algorithm":[435,882],"lead":[437],"scalable":[439,681,696],"expressive":[441,552,708,760],"kernels.":[442],"Moreover,":[443],"survey":[445],"principle":[451],"refinement.":[454],"Finally,":[455],"shed":[457],"light":[459],"connection":[462],"Weisfeiler-Leman-based":[464],"architectures":[468],"graph-structured":[470,474],"input.":[471],"Learning":[472],"molecules,":[478],"social,":[479],"biological,":[480],"financial":[482],"networks,":[483],"requires":[484],"effective":[485],"representations":[486],"successfully":[488],"capture":[489],"their":[490,551,579,809,947],"rich":[491],"structural":[492],"properties.":[493],"years,":[496],"numerous":[497],"approaches":[498,510,682,697],"have":[499,575],"been":[500],"-":[507],"notably,":[509],"Graph":[516,520],"Neural":[517],"Networks":[518],"(GNNs).":[519],"networks":[522,687,731,1020],"exploit":[523],"relational":[524],"inductive":[525],"biases":[526],"following":[532],"differentiable":[534],"message":[536,633,654,711,728],"passing":[537,634,655,729],"scheme,":[538],"show-case":[540],"promising":[541],"performance":[542],"variety":[545],"tasks":[548],"due":[549,920],"power":[553,709,761],"capturing":[555,831],"structures.":[558],"However,":[559],"despite":[560],"indisputable":[562],"potential":[563],"GNNs":[565],"representations,":[569],"challenges":[573],"so":[576],"precluded":[578],"wide":[580,644],"adoption":[581],"industrial":[583],"social":[585],"applications":[586,879],"difficulty":[589],"scale":[591],"graphs.":[595,690,734],"particular,":[597,692,906],"embedding":[599,994,1110],"given":[602],"node":[603,747],"depends":[604],"recursively":[605],"all":[607],"its":[608],"neighbor\u2019s":[609],"embeddings,":[610],"leading":[611],"high":[613],"inter-dependency":[614],"grows":[618],"exponentially":[619],"respect":[621],"layers.":[626],"Here,":[627],"demonstrate":[629],"generality":[631,652],"through":[635],"unified":[637],"framework":[638,724],"suitable":[641],"range":[645],"operators":[647],"tasks.":[650],"led":[656],"PyTorch":[661],"Geometric,":[662],"well-known":[664],"library":[667],"implementing":[669],"working":[671],"graph-based":[673],"building":[676],"blocks.":[677],"applying":[684],"large-scale":[689],"sub-sampling":[700],"edges":[702],"or":[703,846,910],"non-trainable":[704],"propagations":[705],"weaken":[706],"passing.":[712],"order":[714],"overcome":[716],"restriction,":[718],"GNN":[721,735],"AutoScale,":[722],"scaling":[726],"arbitrary":[727],"AutoScale":[736],"prunes":[737],"entire":[738],"sub-trees":[739],"computation":[742],"utilizing":[745],"historical":[746],"embeddings":[748],"prior":[750],"iterations":[752],"while":[753],"provably":[754],"being":[755],"able":[756,1075],"maintain":[758],"original":[764],"architecture.":[765],"engineer":[767],"parallel":[768,842,884],"algorithms":[769,849],"approximating":[771],"maximum":[773],"cut":[774,871],"directed":[778],"graph.":[779],"Our":[780],"general":[781],"approach":[782,974],"first":[785],"partition":[786],"p":[790,793,863],"parts,":[791,864],"where":[792],"denotes":[794],"processing":[798],"elements.":[799],"individual":[801],"processors":[802],"then":[803],"independently":[804],"compute":[805,851],"approximation":[807,818,848],"using":[815,840,1109],"high-quality":[816],"sequential":[817],"algorithms.":[819],"final":[822],"step,":[823],"single":[825],"Max-Dicut":[826],"instance":[827],"size":[829],"O(p2),":[830],"interprocessor":[833],"edges,":[834],"defined":[836],"solved":[838],"exactly,":[839],"fast":[841],"Integer":[843],"Program":[844],"solvers":[845],"slow":[847],"good":[853],"approximation.":[854],"By":[855],"partitioning":[856],"p\u2032":[861],">":[862],"get":[866],"smooth":[868],"trade-off":[869],"quality":[872],"running":[874],"time.":[875],"also":[877],"our":[881,1003,1036,1091,1094],"grammar-based":[885],"text":[886],"compression.":[887],"Amid":[888],"increase":[890],"research":[895],"publications,":[896],"search":[898,1103],"relevant":[900,1013],"papers":[901],"has":[902],"become":[903],"tedious.":[904],"searches":[907],"across":[908],"disciplines":[909],"schools":[911],"thinking":[913],"supported.":[916],"mainly":[919],"retrieval":[923,977],"terms":[925,931],"keyword":[927],"queries,":[928],"technical":[930],"differ":[932],"sciences":[935],"times.":[939],"Relevant":[940],"articles":[941],"might":[942],"better":[943],"identified":[945],"mathematical":[948,979,1014,1023,1047,1113],"problem":[949],"descriptions.":[950],"Just":[951],"looking":[952],"equations":[955],"paper":[958,966,1122],"already":[959],"gives":[960],"hint":[962],"whether":[964],"relevant.":[968],"Hence,":[969],"new":[973],"expressions":[980,1024,1048],"learning.":[984,1000],"design":[986],"unsupervised":[988],"representation":[989,1005],"task":[991],"combines":[993],"learning,":[995,997],"contrastive":[996],"self-supervised":[999],"want":[1002],"learned":[1004],"allow":[1007,1030],"automatic":[1009],"identification":[1010],"related,":[1012],"expressions.":[1015],"Using":[1016],"convolutional":[1018],"embed":[1022],"low-dimensional":[1026],"vector":[1027],"spaces":[1028],"efficient":[1031],"nearestneighbor":[1032],"queries.":[1033],"To":[1034],"train":[1035],"collect":[1039],"huge":[1041],"dataset":[1042,1099],"over":[1044,1050],"29":[1045],"million":[1046],"900":[1051],"000":[1052],"publications":[1053],"arXiv.org.":[1055],"math":[1057],"converted":[1059],"XML":[1062],"format,":[1063],"view":[1066],"data,":[1072],"automatically":[1077],"identify":[1078],"equalities":[1079],"inequalities":[1081],"use":[1085],"testing":[1089],"models.":[1092],"empirical":[1095],"evaluations":[1096],"involve":[1097],"manually":[1101],"annotated":[1102],"queries":[1104],"benefits":[1107],"retrieval.":[1114],"conference":[1121],"[563]":[1123],"more":[1125],"details":[1126],"found":[1129],"[562].":[1131]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2023-01-06T00:00:00"}