{"id":"https://openalex.org/W3010534546","doi":"https://doi.org/10.1145/3318464.3380577","title":"Factorized Graph Representations for Semi-Supervised Learning from Sparse Data","display_name":"Factorized Graph Representations for Semi-Supervised Learning from Sparse Data","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W3010534546","doi":"https://doi.org/10.1145/3318464.3380577","mag":"3010534546"},"language":"en","primary_location":{"id":"doi:10.1145/3318464.3380577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3318464.3380577","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3380577","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3380577","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Krishna Kumar P.","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Krishna Kumar P.","raw_affiliation_strings":["IIT Madras, Madras, India"],"affiliations":[{"raw_affiliation_string":"IIT Madras, Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Paul Langton","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Langton","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wolfgang Gatterbauer","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wolfgang Gatterbauer","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.5438,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72625905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1383","last_page":"1398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9966999888420105,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5712000131607056},{"id":"https://openalex.org/keywords/algebraic-number","display_name":"Algebraic number","score":0.5141000151634216},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4950999915599823},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.49129998683929443},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4059000015258789},{"id":"https://openalex.org/keywords/compatibility","display_name":"Compatibility (geochemistry)","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025000214576721},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5712000131607056},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5429999828338623},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.49129998683929443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.3416999876499176},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3221000134944916},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3318464.3380577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3318464.3380577","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3380577","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.02829","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.02829","pdf_url":"https://arxiv.org/pdf/2003.02829","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3318464.3380577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3318464.3380577","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3380577","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2699994585","display_name":"CAREER: Scaling Approximate Inference and Approximation-Aware Learning","funder_award_id":"1762268","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4327809303","display_name":null,"funder_award_id":"CAREER III-1762268.","funder_id":"https://openalex.org/F4320309856","funder_display_name":"National Youth Science Foundation"},{"id":"https://openalex.org/G5213409069","display_name":null,"funder_award_id":"CAREER IIS-1762268","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309856","display_name":"National Youth Science Foundation","ror":"https://ror.org/054yz2f06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3010534546.pdf","grobid_xml":"https://content.openalex.org/works/W3010534546.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1969198379","https://openalex.org/W1990280147","https://openalex.org/W2024514015","https://openalex.org/W2037859435","https://openalex.org/W2058526570","https://openalex.org/W2063049279","https://openalex.org/W2066710237","https://openalex.org/W2076280956","https://openalex.org/W2082029531","https://openalex.org/W2090081488","https://openalex.org/W2124168655","https://openalex.org/W2138399168","https://openalex.org/W2145901369","https://openalex.org/W2146292423","https://openalex.org/W2148534792","https://openalex.org/W2150449434","https://openalex.org/W2153959628","https://openalex.org/W2162150749","https://openalex.org/W2167149929","https://openalex.org/W2175160295","https://openalex.org/W2177500510","https://openalex.org/W2254563062","https://openalex.org/W2536131596","https://openalex.org/W2552455004","https://openalex.org/W2584187726","https://openalex.org/W2769041395","https://openalex.org/W2954348559","https://openalex.org/W2963294336","https://openalex.org/W2997591727","https://openalex.org/W3032120536","https://openalex.org/W4230094279"],"related_works":[],"abstract_inverted_index":{"Node":[0],"classification":[1,178],"is":[2,11,97,165,180],"an":[3,150],"important":[4],"problem":[5],"in":[6,94,99,158],"graph":[7,119,134],"data":[8],"management.":[9],"It":[10],"commonly":[12],"solved":[13],"by":[14,53,166],"various":[15],"label":[16,109,197],"propagation":[17,198],"methods":[18,40],"that":[19,162,175],"iteratively":[20],"pass":[21],"messages":[22],"along":[23],"edges,":[24],"starting":[25],"from":[26,72],"a":[27,62,73,100,190],"few":[28],"labeled":[29,75,90],"seed":[30],"nodes.":[31,112],"For":[32],"graphs":[33,91],"with":[34],"arbitrary":[35],"compatibilities":[36,71],"between":[37],"classes,":[38],"these":[39,132],"crucially":[41],"depend":[42],"on":[43,87,131,205],"knowing":[44],"the":[45,70,103,110,125,142,176,202],"compatibility":[46,83],"matrix,":[47],"which":[48,79],"must":[49],"thus":[50],"be":[51],"provided":[52],"either":[54],"domain":[55],"experts":[56],"or":[57],"heuristics.":[58,206],"We":[59,136,160],"instead":[60],"suggest":[61],"principled":[63],"and":[64,127,174,200],"scalable":[65],"method":[66,199],"for":[67,194],"directly":[68],"estimating":[69],"sparsely":[74,89],"graph.":[76],"This":[77,187],"method,":[78],"we":[80],"call":[81],"distant":[82],"estimation,":[84],"works":[85],"even":[86],"extremely":[88],"(e.g.,":[92],"1":[93],"10,000":[95],"nodes":[96],"labeled)":[98],"fraction":[101],"of":[102,124,145,149,168],"time":[104],"it":[105,189],"later":[106],"takes":[107],"to":[108,138,154,182],"remaining":[111],"Our":[113],"approach":[114],"first":[115],"creates":[116],"multiple":[117],"factorized":[118],"representations":[120],"(with":[121],"size":[122],"independent":[123],"graph)":[126],"then":[128],"performs":[129],"estimation":[130],"smaller":[133],"sketches.":[135],"refer":[137],"algebraic":[139,147],"amplification":[140],"as":[141],"underlying":[143],"idea":[144],"leveraging":[146],"properties":[148],"algorithm's":[151],"update":[152],"equations":[153],"amplify":[155],"sparse":[156],"signals":[157],"data.":[159],"show":[161],"our":[163],"estimator":[164],"orders":[167],"magnitude":[169],"faster":[170],"than":[171],"alternative":[172],"approaches":[173],"end-to-end":[177],"accuracy":[179],"comparable":[181],"using":[183],"gold":[184],"standard":[185],"compatibilities.":[186],"makes":[188],"cheap":[191],"pre-processing":[192],"step":[193],"any":[195],"existing":[196],"removes":[201],"current":[203],"dependence":[204]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2020-03-13T00:00:00"}