{"id":"https://openalex.org/W4408355152","doi":"https://doi.org/10.1109/icassp49660.2025.10890404","title":"HFLR: Optimizing GNN Training via High-Fixed-Low-Resampling","display_name":"HFLR: Optimizing GNN Training via High-Fixed-Low-Resampling","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355152","doi":"https://doi.org/10.1109/icassp49660.2025.10890404"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5068006653","display_name":"Chang Gong","orcid":"https://orcid.org/0000-0002-8287-3029"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Gong","raw_affiliation_strings":["Fudan University,School of Data Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Data Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090727114","display_name":"Boyu Yang","orcid":"https://orcid.org/0009-0002-3990-1634"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Yang","raw_affiliation_strings":["Fudan University,School of Data Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Data Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101658368","display_name":"Weiguo Zheng","orcid":"https://orcid.org/0000-0003-1200-7368"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguo Zheng","raw_affiliation_strings":["Fudan University,School of Data Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Data Science,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06906385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.8687000274658203,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.8687000274658203,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7138973474502563},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6388798952102661},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5795702934265137},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4236522316932678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30176842212677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138973474502563},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6388798952102661},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5795702934265137},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4236522316932678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30176842212677},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":28,"referenced_works":["https://openalex.org/W2807021761","https://openalex.org/W2913560138","https://openalex.org/W2945827377","https://openalex.org/W2984343629","https://openalex.org/W2990045899","https://openalex.org/W3019011053","https://openalex.org/W3152893301","https://openalex.org/W3167254314","https://openalex.org/W4307323725","https://openalex.org/W4404932443","https://openalex.org/W6639055396","https://openalex.org/W6726873649","https://openalex.org/W6730084236","https://openalex.org/W6736685754","https://openalex.org/W6738964360","https://openalex.org/W6748799445","https://openalex.org/W6748848838","https://openalex.org/W6748856961","https://openalex.org/W6753331806","https://openalex.org/W6754030515","https://openalex.org/W6754929296","https://openalex.org/W6765543928","https://openalex.org/W6766609504","https://openalex.org/W6766978945","https://openalex.org/W6767710714","https://openalex.org/W6776488958","https://openalex.org/W6779961489","https://openalex.org/W6784629068"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2052515325","https://openalex.org/W2050948537","https://openalex.org/W2767646790","https://openalex.org/W2352041579","https://openalex.org/W1488006380","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Training":[0],"graph":[1],"neural":[2],"networks":[3],"(GNNs)":[4],"on":[5,124],"large-scale":[6,126],"graphs":[7,38,127],"is":[8,69],"challenging":[9],"due":[10],"to":[11,75],"neighbor":[12],"explosion":[13],"problem.":[14],"To":[15,109],"alleviate":[16],"this,":[17],"various":[18],"sampling":[19,52],"methods":[20],"have":[21],"been":[22],"proposed.":[23],"However,":[24],"they":[25],"still":[26],"suffer":[27],"from":[28,46],"several":[29],"issues":[30],"like":[31],"sparse":[32],"relationships":[33],"between":[34],"layers":[35],"of":[36,61,87,114],"computation":[37],"or":[39],"edge":[40],"information":[41],"loss":[42,91],"during":[43],"sampling.":[44],"Different":[45],"them,":[47],"we":[48,82,117],"propose":[49],"a":[50,58,84],"novel":[51],"strategy":[53],"named":[54],"HFLR,":[55],"which":[56],"uses":[57],"small":[59,85],"subset":[60],"total":[62],"nodes":[63,73,88],"for":[64,89,99],"training.":[65],"The":[66],"basic":[67],"principle":[68],"that":[70],"not":[71],"all":[72,100],"contribute":[74],"accuracy":[76],"improvement.":[77],"Specifically,":[78],"in":[79,106],"each":[80,107],"epoch,":[81],"sample":[83],"number":[86],"computing":[90],"and":[92],"updating":[93],"parameters,":[94],"where":[95],"some":[96],"are":[97,104],"fixed":[98],"epochs,":[101],"while":[102],"others":[103],"resampled":[105],"epoch.":[108],"guarantee":[110],"an":[111],"unbiased":[112],"estimation":[113],"training":[115],"loss,":[116],"further":[118],"present":[119],"normalization":[120],"techniques.":[121],"Extensive":[122],"experiments":[123],"six":[125],"demonstrate":[128],"our":[129],"method":[130],"achieves":[131],"comparable":[132],"F1scores":[133],"with":[134],"1.7x-3.3x":[135],"speedups":[136],"over":[137],"other":[138],"sampling-based":[139],"algorithms.":[140]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}