{"id":"https://openalex.org/W4229034430","doi":"https://doi.org/10.1145/3477314.3507113","title":"Learning on streaming graphs with experience replay","display_name":"Learning on streaming graphs with experience replay","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4229034430","doi":"https://doi.org/10.1145/3477314.3507113"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507113","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507113","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","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 37th ACM/SIGAPP Symposium on Applied Computing","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/A5002837048","display_name":"Massimo Perini","orcid":"https://orcid.org/0000-0001-5006-9979"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Massimo Perini","raw_affiliation_strings":["The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048076721","display_name":"Giorgia Ramponi","orcid":"https://orcid.org/0000-0002-3076-5448"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Giorgia Ramponi","raw_affiliation_strings":["ETH Zurich"],"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039432313","display_name":"Paris Carbone","orcid":"https://orcid.org/0000-0002-9351-8508"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Paris Carbone","raw_affiliation_strings":["KTH Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068567119","display_name":"Vasiliki Kalavri","orcid":"https://orcid.org/0000-0001-8219-4862"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasiliki Kalavri","raw_affiliation_strings":["Boston University"],"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002837048"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.2523,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81266561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"470","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9990000128746033,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9990000128746033,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9944000244140625,"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/T11478","display_name":"Caching and Content Delivery","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.822741687297821},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4900919198989868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48987171053886414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4653433561325073},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.46304136514663696},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45851871371269226},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.44106823205947876},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4160221219062805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822741687297821},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4900919198989868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48987171053886414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4653433561325073},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.46304136514663696},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45851871371269226},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.44106823205947876},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4160221219062805},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477314.3507113","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507113","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","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 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1888005072","https://openalex.org/W2099454382","https://openalex.org/W2141559645","https://openalex.org/W2142535891","https://openalex.org/W2154851992","https://openalex.org/W2393319904","https://openalex.org/W2560647685","https://openalex.org/W2612872092","https://openalex.org/W2623187518","https://openalex.org/W2787927827","https://openalex.org/W2788919350","https://openalex.org/W2798918712","https://openalex.org/W2806983170","https://openalex.org/W2807021761","https://openalex.org/W2808087697","https://openalex.org/W2808908091","https://openalex.org/W2809418595","https://openalex.org/W2898104583","https://openalex.org/W2945726694","https://openalex.org/W2945827377","https://openalex.org/W2954691982","https://openalex.org/W2962756421","https://openalex.org/W2963066159","https://openalex.org/W2963280944","https://openalex.org/W2963588172","https://openalex.org/W2969696968","https://openalex.org/W2985848516","https://openalex.org/W3018483767","https://openalex.org/W3019863187","https://openalex.org/W3026076535","https://openalex.org/W3087775916","https://openalex.org/W3098366174","https://openalex.org/W3100848837","https://openalex.org/W3101553402","https://openalex.org/W3103254545","https://openalex.org/W3104097132","https://openalex.org/W4394669517","https://openalex.org/W6601487527","https://openalex.org/W6604404400","https://openalex.org/W6920860091"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2066741154","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W2082556335","https://openalex.org/W322691623","https://openalex.org/W2494989134"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"recently":[5],"achieved":[6],"good":[7],"performance":[8,127],"in":[9,76],"many":[10],"predictive":[11],"tasks":[12],"involving":[13],"graph-structured":[14],"data.":[15],"However,":[16],"the":[17,49,64,77,102,123,134],"majority":[18],"of":[19,66,108,128,142,156],"existing":[20],"models":[21,106],"consider":[22],"static":[23],"graphs":[24,112,141],"only":[25,46],"and":[26,53,88,117,125,145,152,169],"do":[27],"not":[28],"support":[29],"training":[30,84,115,126,159],"on":[31,133],"graph":[32,51,73],"streams.":[33],"While":[34],"inductive":[35],"representation":[36,74],"learning":[37,75],"can":[38],"generate":[39],"predictions":[40],"for":[41],"unseen":[42],"vertices,":[43],"these":[44,129],"are":[45,101],"accurate":[47],"if":[48],"learned":[50],"structure":[52],"properties":[54],"remain":[55],"stable":[56],"over":[57],"time.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"study":[63],"problem":[65,137],"employing":[67],"experience":[68,130],"replay":[69,131],"to":[70,110,162,171],"enable":[71],"continuous":[72],"streaming":[78,104,140],"setting.":[79],"We":[80,121],"propose":[81],"two":[82],"online":[83],"methods,":[85],"Random-Based":[86],"Rehearsal-RBR,":[87],"Priority-Based":[89],"Rehearsal-PBR,":[90],"which":[91],"avoid":[92],"retraining":[93],"from":[94],"scratch":[95],"when":[96],"changes":[97],"occur.":[98],"Our":[99,147],"algorithms":[100],"first":[103],"GNN":[105],"capable":[107],"scaling":[109],"million-edge":[111],"with":[113],"low":[114],"latency":[116],"without":[118],"compromising":[119],"accuracy.":[120],"evaluate":[122],"accuracy":[124,168],"methods":[132,164],"node":[135],"classification":[136],"using":[138],"real-world":[139],"various":[143],"sizes":[144],"domains.":[146],"results":[148],"demonstrate":[149],"that":[150],"PBR":[151],"RBR":[153],"achieve":[154],"orders":[155],"magnitude":[157],"faster":[158],"as":[160],"compared":[161],"offline":[163],"while":[165],"providing":[166],"high":[167],"resiliency":[170],"concept":[172],"drift.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}