{"id":"https://openalex.org/W7123818652","doi":"https://doi.org/10.1145/3772052.3772253","title":"FaaSGNN: Enabling Memory Efficient and Low Latency GNN Inference Services with Serverless Computing","display_name":"FaaSGNN: Enabling Memory Efficient and Low Latency GNN Inference Services with Serverless Computing","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7123818652","doi":"https://doi.org/10.1145/3772052.3772253"},"language":null,"primary_location":{"id":"doi:10.1145/3772052.3772253","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772052.3772253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Cloud 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/A5102754039","display_name":"Yuzhuo Yang","orcid":"https://orcid.org/0009-0003-7494-9219"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuzhuo Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-7494-9219","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037447327","display_name":"Kaihua Fu","orcid":"https://orcid.org/0000-0001-5117-7162"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaihua Fu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5117-7162","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122928046","display_name":"Quan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5832-0347","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122861914","display_name":"Deze Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deze Zeng","raw_affiliation_strings":["China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3276-1202","affiliations":[{"raw_affiliation_string":"China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040978935","display_name":"Shuo Quan","orcid":"https://orcid.org/0000-0001-8824-631X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Quan","raw_affiliation_strings":["Cloud Computing Research Institute, China Telecom, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8824-631X","affiliations":[{"raw_affiliation_string":"Cloud Computing Research Institute, China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I4210136246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122914085","display_name":"Jie Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["Temple University, Philadelphia, United States"],"raw_orcid":"https://orcid.org/0000-0002-3472-1717","affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, United States","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120913770","display_name":"Minyi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0034-2302","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102754039"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78704354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"816"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.5472000241279602,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.5472000241279602,"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/T11478","display_name":"Caching and Content Delivery","score":0.1152999997138977,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.05290000140666962,"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/latency","display_name":"Latency (audio)","score":0.714900016784668},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6880000233650208},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.4837000072002411},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.46790000796318054},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41440001130104065},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392999768257141},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.714900016784668},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6880000233650208},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C2777480716","wikidata":"https://www.wikidata.org/wiki/Q23582796","display_name":"Resource consumption","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772052.3772253","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772052.3772253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.46827682852745056,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G6491789219","display_name":null,"funder_award_id":"62232011, 62432015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2899457523","https://openalex.org/W2970929262","https://openalex.org/W2977714483","https://openalex.org/W3009901425","https://openalex.org/W3094621775","https://openalex.org/W3096566397","https://openalex.org/W3112094022","https://openalex.org/W3130689885","https://openalex.org/W3152809665","https://openalex.org/W3155705005","https://openalex.org/W3155936517","https://openalex.org/W3159401322","https://openalex.org/W3207498965","https://openalex.org/W4214610523","https://openalex.org/W4214690606","https://openalex.org/W4214761305","https://openalex.org/W4220807331","https://openalex.org/W4293024973","https://openalex.org/W4294904165","https://openalex.org/W4306317696","https://openalex.org/W4360831816","https://openalex.org/W4380091476","https://openalex.org/W4385075286","https://openalex.org/W4385567729","https://openalex.org/W4396758741","https://openalex.org/W4405756303","https://openalex.org/W4408441875"],"related_works":[],"abstract_inverted_index":{"While":[0],"GNN-based":[1],"services":[2],"often":[3],"experience":[4],"load":[5,125],"fluctuation,":[6],"applying":[7],"serverless":[8,24,60],"computing":[9],"to":[10,29,107,119,148],"serve":[11],"GNN":[12,23,61,71],"inference":[13,62],"reduces":[14],"the":[15],"cost":[16],"and":[17,34,39,48,68,111,123,140],"allows":[18],"elastic":[19],"resource":[20],"scaling.":[21],"However,":[22],"shows":[25],"poor":[26],"performance":[27],"due":[28],"heavy":[30],"data":[31,46,103],"fetching":[32,81],"latency":[33,67,139],"long":[35],"cold":[36,50,121],"startup":[37,51],"overhead,":[38],"our":[40],"observation":[41],"indicates":[42],"opportunities":[43],"for":[44],"reducing":[45],"redundancy":[47],"mitigating":[49],"latency.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"present":[57],"FaaSGNN,":[58],"a":[59,135],"framework":[63],"that":[64,83,132],"enables":[65,84],"low":[66],"memory":[69,143],"efficient":[70],"serving":[72],"through":[73],"three":[74],"key":[75],"designs:":[76],"(i)":[77],"serverless-native":[78],"on-demand":[79],"graph":[80,87],"strategy":[82],"lightweight":[85],"in-container":[86],"sampling":[88],"with":[89],"full":[90],"dataset":[91],"resides":[92],"in":[93],"remote;":[94],"(ii)":[95],"memory-aware":[96],"adaptive":[97],"feature":[98],"caching":[99],"policy,":[100],"which":[101,116],"facilitates":[102],"reuse":[104],"between":[105,127],"requests":[106,118],"reduce":[108],"redundant":[109],"fetching;":[110],"(iii)":[112],"load-aware":[113],"request":[114],"scheduler,":[115],"reschedules":[117],"bypass":[120],"start":[122],"achieve":[124],"balance":[126],"containers.":[128],"Experimental":[129],"results":[130],"show":[131],"FaaSGNN":[133],"achieves":[134],"5.6x":[136],"lower":[137],"end-to-end":[138],"57.1%":[141],"less":[142],"usage":[144],"on":[145],"average":[146],"compared":[147],"state-of-the-art":[149],"works.":[150]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-14T00:00:00"}