{"id":"https://openalex.org/W4221143762","doi":"https://doi.org/10.1145/3485447.3512206","title":"Compact Graph Structure Learning via Mutual Information Compression","display_name":"Compact Graph Structure Learning via Mutual Information Compression","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4221143762","doi":"https://doi.org/10.1145/3485447.3512206"},"language":"en","primary_location":{"id":"doi:10.1145/3485447.3512206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3512206","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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 ACM Web Conference 2022","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/A5114626653","display_name":"Nian Liu","orcid":"https://orcid.org/0000-0002-5975-0661"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nian Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411426","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0001-6117-6745"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101478122","display_name":"Lingfei Wu","orcid":"https://orcid.org/0009-0008-8081-6275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingfei Wu","raw_affiliation_strings":["JD.com Silicon Valley Research Center, USA"],"affiliations":[{"raw_affiliation_string":"JD.com Silicon Valley Research Center, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402071","display_name":"Yu Chen","orcid":"https://orcid.org/0000-0002-8118-7262"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Chen","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930629","display_name":"Xiaojie Guo","orcid":"https://orcid.org/0000-0002-1946-1179"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojie Guo","raw_affiliation_strings":["JD.com Silicon Valley Research Center, USA"],"affiliations":[{"raw_affiliation_string":"JD.com Silicon Valley Research Center, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705849","display_name":"Chuan Shi","orcid":"https://orcid.org/0000-0002-3734-0266"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Shi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114626653"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":4.0909,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95150519,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1601","last_page":"1610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":1.0,"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":1.0,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9731000065803528,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7013806104660034},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6368916034698486},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5778734683990479},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.540298342704773},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5248508453369141},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5230827331542969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4326492249965668},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3882494568824768},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32349008321762085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1769179403781891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013806104660034},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6368916034698486},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5778734683990479},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.540298342704773},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5248508453369141},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5230827331542969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4326492249965668},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3882494568824768},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32349008321762085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1769179403781891},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3485447.3512206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3512206","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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 ACM Web Conference 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2907492528","https://openalex.org/W2912083425","https://openalex.org/W2948729509","https://openalex.org/W2970398671","https://openalex.org/W3081203761","https://openalex.org/W3153206160","https://openalex.org/W3175971420","https://openalex.org/W4250735360"],"related_works":["https://openalex.org/W2466816617","https://openalex.org/W1970834875","https://openalex.org/W3174028392","https://openalex.org/W842936808","https://openalex.org/W4287880334","https://openalex.org/W2000517284","https://openalex.org/W4366700029","https://openalex.org/W2136503713","https://openalex.org/W2365318811","https://openalex.org/W2375330620"],"abstract_inverted_index":{"Graph":[0,23],"Structure":[1],"Learning":[2],"(GSL)":[3],"recently":[4],"has":[5],"attracted":[6],"considerable":[7],"attentions":[8],"in":[9,102],"its":[10],"capacity":[11],"of":[12,22,167,197,209,218,238],"optimizing":[13],"graph":[14,35,56,65,163],"structure":[15,36,57,66,101],"as":[16,18,78,80,85,90,164],"well":[17],"learning":[19],"suitable":[20],"parameters":[21],"Neural":[24],"Networks":[25],"(GNNs)":[26],"simultaneously.":[27],"Current":[28],"GSL":[29,148],"methods":[30],"mainly":[31],"learn":[32],"an":[33,63,181],"optimal":[34,55,64],"(final":[37],"view)":[38],"from":[39,161],"single":[40],"or":[41],"multiple":[42],"information":[43,71,208],"sources":[44],"(basic":[45],"views),":[46],"however":[47],"the":[48,54,70,93,132,168,189,195,201,206,216,234],"theoretical":[49],"guidance":[50],"on":[51,122,129,224],"what":[52],"is":[53,58,83],"still":[59],"unexplored.":[60],"In":[61,106],"essence,":[62],"should":[67],"only":[68],"contain":[69],"about":[72],"tasks":[73],"while":[74],"compress":[75],"redundant":[76],"noise":[77],"much":[79],"possible,":[81],"which":[82,170,232],"defined":[84],"\u201dminimal":[86],"sufficient":[87,139],"structure\u201d,":[88],"so":[89],"to":[91,98,184],"maintain":[92,194],"accurancy":[94],"and":[95,118,125,200,204,229,236],"robustness.":[96],"How":[97],"obtain":[99],"such":[100],"a":[103,137,146,175],"principled":[104],"way?":[105],"this":[107,142],"paper,":[108],"we":[109,114,144,179,193,220],"theoretically":[110],"prove":[111],"that":[112],"if":[113],"optimize":[115],"basic":[116,157],"views":[117,158,187,199],"final":[119,133,190,202],"view":[120,134,176,203],"based":[121],"mutual":[123,207],"information,":[124],"keep":[126],"their":[127],"performance":[128,196,217],"labels":[130],"simultaneously,":[131],"will":[135],"be":[136],"minimal":[138],"structure.":[140],"With":[141],"guidance,":[143],"propose":[145,180],"Compact":[147],"architecture":[149],"by":[150,174],"MI":[151],"compression,":[152],"named":[153],"CoGSL.":[154,239],"Specifically,":[155],"two":[156,165,211],"are":[159,171],"extracted":[160],"original":[162],"inputs":[166],"model,":[169],"refinedly":[172],"reestimated":[173],"estimator.":[177],"Then,":[178],"adaptive":[182],"technique":[183],"fuse":[185],"estimated":[186,198],"into":[188],"view.":[191],"Furthermore,":[192],"reduce":[205],"every":[210],"views.":[212],"To":[213],"comprehensively":[214],"evaluate":[215],"CoGSL,":[219],"conduct":[221],"extensive":[222],"experiments":[223],"several":[225],"datasets":[226],"under":[227],"clean":[228],"attacked":[230],"conditions,":[231],"demonstrate":[233],"effectiveness":[235],"robustness":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}