{"id":"https://openalex.org/W4409158058","doi":"https://doi.org/10.1145/3690624.3709241","title":"Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification","display_name":"Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409158058","doi":"https://doi.org/10.1145/3690624.3709241"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","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/A5078998839","display_name":"Haipeng Ding","orcid":"https://orcid.org/0009-0006-4856-3023"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haipeng Ding","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074858555","display_name":"Zhewei Wei","orcid":"https://orcid.org/0000-0003-3620-5086"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhewei Wei","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074630934","display_name":"Yuhang Ye","orcid":"https://orcid.org/0009-0003-4277-766X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Ye","raw_affiliation_strings":["Huawei Poisson Lab, Huawei Technologies Ltd., Guangzhou, Guangdong Province, China"],"affiliations":[{"raw_affiliation_string":"Huawei Poisson Lab, Huawei Technologies Ltd., Guangzhou, Guangdong Province, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078998839"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02914789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"223"},"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":0.9965999722480774,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9876000285148621,"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/computer-science","display_name":"Computer science","score":0.6642823815345764},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49271324276924133},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47690701484680176},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3457869291305542},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.090628981590271},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06968030333518982}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6642823815345764},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49271324276924133},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47690701484680176},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3457869291305542},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.090628981590271},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06968030333518982}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3690624.3709241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","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":29,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1800323139","https://openalex.org/W1932742904","https://openalex.org/W1997315949","https://openalex.org/W2027731328","https://openalex.org/W2045107949","https://openalex.org/W2125664420","https://openalex.org/W2129575457","https://openalex.org/W2153959628","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2807021761","https://openalex.org/W2899457523","https://openalex.org/W2914833637","https://openalex.org/W2945827377","https://openalex.org/W2996451395","https://openalex.org/W3039500550","https://openalex.org/W3090863228","https://openalex.org/W3100848837","https://openalex.org/W3101543043","https://openalex.org/W3101553402","https://openalex.org/W3101707147","https://openalex.org/W3103311102","https://openalex.org/W3152560880","https://openalex.org/W3154818219","https://openalex.org/W3172620719","https://openalex.org/W3190794503","https://openalex.org/W4383982659","https://openalex.org/W4385568130"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Graph":[0,109],"Neural":[1,110],"Networks":[2,111],"(GNNs)":[3],"play":[4],"a":[5,84,116],"pivotal":[6],"role":[7],"in":[8,14,209],"graph-based":[9],"tasks":[10,32],"for":[11],"their":[12],"proficiency":[13],"representation":[15],"learning.":[16],"Among":[17],"the":[18,54,76,80,103,124,154,160,170,192,212],"various":[19,185],"GNN":[20],"methods,":[21],"spectral":[22,44,72,119,128],"GNNs":[23,45,73],"employing":[24],"polynomial":[25,55,146],"filters":[26,147],"have":[27,67],"shown":[28],"promising":[29],"performance":[30],"on":[31,46,79,159,182,218],"involving":[33],"both":[34,142],"homophilous":[35],"and":[36,94,144,188,195,224],"heterophilous":[37],"graph":[38,118,186],"structures.":[39],"However,":[40],"The":[41,200],"scalability":[42],"of":[43,127,156,172,197],"large":[47],"graphs":[48],"is":[49],"limited":[50],"because":[51],"they":[52],"learn":[53],"coefficients":[56],"through":[57],"multiple":[58],"forward":[59,63],"propagation":[60,125],"executions":[61],"during":[62],"propagation.":[64],"Existing":[65],"works":[66],"attempted":[68],"to":[69,122,190],"scale":[70],"up":[71],"by":[74],"eliminating":[75],"linear":[77,157],"layers":[78,158],"input":[81,99,161],"node":[82,162],"features,":[83,163],"change":[85],"that":[86,132,139,203],"can":[87,140],"disrupt":[88],"end-to-end":[89,165],"training,":[90],"potentially":[91],"impact":[92],"performance,":[93],"become":[95],"impractical":[96],"with":[97,112,148,211],"high-dimensional":[98],"features.":[100,175],"To":[101],"address":[102],"above":[104],"challenges,":[105],"we":[106],"propose":[107],"''Spectral":[108],"Laplacian":[113,137],"Sparsification":[114],"(SGNN-LS)'',":[115],"novel":[117],"sparsification":[120],"method":[121,135,152,205],"approximate":[123,141],"patterns":[126],"GNNs.":[129],"We":[130,176],"prove":[131],"our":[133,198,204],"proposed":[134],"generates":[136],"sparsifiers":[138],"fixed":[143],"learnable":[145],"theoretical":[149],"guarantees.":[150],"Our":[151],"allows":[153],"application":[155],"enabling":[164],"training":[166],"as":[167,169],"well":[168],"handling":[171],"raw":[173],"text":[174],"conduct":[177],"an":[178],"extensive":[179],"experimental":[180],"analysis":[181],"datasets":[183],"spanning":[184],"scales":[187],"properties":[189],"demonstrate":[191],"superior":[193,207],"efficiency":[194],"effectiveness":[196],"method.":[199],"results":[201,208],"show":[202],"yields":[206],"comparison":[210],"corresponding":[213],"approximated":[214],"base":[215],"models,":[216],"especially":[217],"dataset":[219],"Ogbn-papers100M(111M":[220],"nodes,":[221],"1.6B":[222],"edges)":[223],"MAG-scholar-C":[225],"(2.8M":[226],"features).":[227]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}