{"id":"https://openalex.org/W4321480027","doi":"https://doi.org/10.1145/3539597.3570455","title":"Self-Supervised Graph Structure Refinement for Graph Neural Networks","display_name":"Self-Supervised Graph Structure Refinement for Graph Neural Networks","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321480027","doi":"https://doi.org/10.1145/3539597.3570455"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","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/A5103004802","display_name":"Jianan Zhao","orcid":"https://orcid.org/0000-0002-9743-7588"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianan Zhao","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006218899","display_name":"Qianlong Wen","orcid":"https://orcid.org/0000-0003-3812-8395"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qianlong Wen","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000740265","display_name":"Mingxuan Ju","orcid":"https://orcid.org/0000-0003-0519-7829"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingxuan Ju","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022275632","display_name":"Chuxu Zhang","orcid":"https://orcid.org/0000-0002-8349-7926"},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuxu Zhang","raw_affiliation_strings":["Brandeis University, Waltham, MA, USA"],"affiliations":[{"raw_affiliation_string":"Brandeis University, Waltham, MA, USA","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027601906","display_name":"Yanfang Ye","orcid":"https://orcid.org/0000-0002-6038-2173"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanfang Ye","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103004802"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":3.8462,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9462869,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"167"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9890000224113464,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.978600025177002,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.7649634480476379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7533524036407471},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.574018657207489},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.573465883731842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239558219909668},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5161107778549194},{"id":"https://openalex.org/keywords/adjacency-list","display_name":"Adjacency list","score":0.45877110958099365},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4284519851207733},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41498520970344543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2729899287223816}],"concepts":[{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.7649634480476379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533524036407471},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.574018657207489},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.573465883731842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239558219909668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5161107778549194},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.45877110958099365},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4284519851207733},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41498520970344543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2729899287223816},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7166937732","display_name":null,"funder_award_id":"IIS-2209814, IIS-2203262, IIS-2214376, IIS-2217239, OAC-2218762, CNS-2203261, CNS-2122631, CMMI-2146076","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2070689335","https://openalex.org/W2154851992","https://openalex.org/W2583803680","https://openalex.org/W2807021761","https://openalex.org/W2808927717","https://openalex.org/W2904965361","https://openalex.org/W2945827670","https://openalex.org/W2963456618","https://openalex.org/W2965857891","https://openalex.org/W2966398094","https://openalex.org/W2984239289","https://openalex.org/W3036446966","https://openalex.org/W3039075121","https://openalex.org/W3080997787","https://openalex.org/W3081203761","https://openalex.org/W3090999459","https://openalex.org/W3099152386","https://openalex.org/W3100278010","https://openalex.org/W3100848837","https://openalex.org/W3100993589","https://openalex.org/W3104097132","https://openalex.org/W3175971420","https://openalex.org/W3190141738","https://openalex.org/W3200170138","https://openalex.org/W3208513668","https://openalex.org/W4290875392","https://openalex.org/W4306317811","https://openalex.org/W4311079930","https://openalex.org/W6600248585","https://openalex.org/W6601487527","https://openalex.org/W6733130978"],"related_works":["https://openalex.org/W4213150077","https://openalex.org/W2369410163","https://openalex.org/W2059018062","https://openalex.org/W2604585036","https://openalex.org/W2078477160","https://openalex.org/W1989103179","https://openalex.org/W1991172810","https://openalex.org/W125803343","https://openalex.org/W2153421018","https://openalex.org/W2117632582"],"abstract_inverted_index":{"Graph":[0],"structure":[1,120,139,157,194,207],"learning":[2,33,89,144],"(GSL),":[3],"which":[4,212],"aims":[5,132],"to":[6,79,133,166,235,256],"learn":[7,80],"the":[8,22,36,63,66,76,81,87,102,109,136,155,167,172,176,182,191,198,209,219,237,257,264],"adjacency":[9,38,110],"matrix":[10,39],"for":[11,45],"graph":[12,84,119,138,156,193,206],"neural":[13],"networks":[14],"(GNNs),":[15],"has":[16],"shown":[17],"great":[18,214],"potential":[19,82],"in":[20,95,197,208],"boosting":[21],"performance":[23,240],"of":[24,65,71,97,104,108,263],"GNNs.":[25],"Most":[26],"existing":[27],"GSL":[28,50,77,259],"works":[29],"apply":[30],"a":[31,53,118,125,141],"joint":[32,88],"framework":[34,90,123,145],"where":[35],"estimated":[37,170],"and":[40,99,106,149,162,185,204,216,228,246],"GNN":[41,178,221],"parameters":[42],"are":[43,233],"optimized":[44,186],"downstream":[46,67,188],"tasks.":[47,153,189],"However,":[48],"as":[49],"is":[51,158,179,222],"essentially":[52],"link":[54,151],"prediction":[55,152],"task,":[56],"whose":[57],"goal":[58,64],"may":[59],"largely":[60],"differ":[61],"from":[62,92],"task.":[68],"The":[69,129],"inconsistency":[70],"these":[72,114],"two":[73],"goals":[74],"limits":[75],"methods":[78],"optimal":[83],"structure.":[85],"Moreover,":[86,218],"suffers":[91],"scalability":[93,215,247],"issues":[94],"terms":[96],"time":[98],"space":[100],"during":[101],"process":[103],"estimation":[105],"optimization":[107],"matrix.":[111],"To":[112],"mitigate":[113],"issues,":[115],"we":[116],"propose":[117],"refinement":[121],"(GSR)":[122],"with":[124,146],"pretrain-finetune":[126],"pipeline.":[127],"Specifically,":[128],"pre-training":[130],"phase":[131,211],"comprehensively":[134],"estimate":[135],"underlying":[137],"by":[140,160,171,181,224],"multi-view":[142],"contrastive":[143],"both":[147,225],"intra-":[148],"inter-view":[150],"Then,":[154],"refined":[159,192],"adding":[161],"removing":[163],"edges":[164],"according":[165],"edge":[168],"probabilities":[169],"pre-trained":[173,183],"model.":[174,266],"Finally,":[175],"fine-tuning":[177,199,210,220],"initialized":[180],"model":[184],"toward":[187],"With":[190],"remaining":[195],"static":[196],"space,":[200],"GSR":[201],"avoids":[202],"estimating":[203],"optimizing":[205],"enjoys":[213],"efficiency.":[217],"boosted":[223],"migrating":[226],"knowledge":[227],"refining":[229],"graphs.":[230],"Extensive":[231],"experiments":[232],"conducted":[234],"evaluate":[236],"effectiveness":[238],"(best":[239],"on":[241,261],"six":[242],"benchmark":[243],"datasets),":[244],"efficiency,":[245],"(13.8":[248],"times":[249],"faster":[250],"using":[251],"32.8%":[252],"GPU":[253],"memory":[254],"compared":[255],"best":[258],"baseline":[260],"Cora)":[262],"proposed":[265]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}