{"id":"https://openalex.org/W7125377740","doi":"https://doi.org/10.48550/arxiv.2601.15079","title":"LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training","display_name":"LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training","publication_year":2026,"publication_date":"2026-01-21","ids":{"openalex":"https://openalex.org/W7125377740","doi":"https://doi.org/10.48550/arxiv.2601.15079"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.15079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.15079","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.15079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100731335","display_name":"Chenyu Liu","orcid":"https://orcid.org/0000-0002-3654-1824"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Chenyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123591152","display_name":"Haige Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haige","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069257022","display_name":"Luca Rossi","orcid":"https://orcid.org/0000-0002-3629-2039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rossi, Luca","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100731335"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9325000047683716,"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":0.9325000047683716,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.010599999688565731,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.00839999970048666,"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/quantization","display_name":"Quantization (signal processing)","score":0.6333000063896179},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6299999952316284},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.607699990272522},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5896000266075134},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5246999859809875},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.34380000829696655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138000130653381},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6333000063896179},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.607699990272522},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5072000026702881},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40130001306533813},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.15079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.15079","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.15079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.15079","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"are":[4],"neural":[5],"networks":[6],"that":[7,84,134],"aim":[8],"to":[9,43,61,70,115],"process":[10],"graph":[11,48,131],"data,":[12,69],"capturing":[13],"the":[14,21,57,67,72,82,86,95,117,138],"relationships":[15],"and":[16,36],"interactions":[17],"between":[18],"nodes":[19],"using":[20],"message-passing":[22],"mechanism.":[23],"GNN":[24],"quantization":[25,44],"has":[26],"emerged":[27],"as":[28],"a":[29,146],"promising":[30],"approach":[31],"for":[32,78],"reducing":[33],"model":[34],"size":[35],"accelerating":[37],"inference":[38],"in":[39,45,53],"resource-constrained":[40],"environments.":[41],"Compared":[42],"LLMs,":[46],"quantizing":[47],"features":[49,88],"is":[50],"more":[51],"emphasized":[52],"GNNs.":[54,79],"Inspired":[55],"by":[56],"above,":[58],"we":[59,100],"propose":[60],"leverage":[62],"prompt":[63],"learning,":[64],"which":[65,106],"manipulates":[66],"input":[68],"improve":[71],"performance":[73,139],"of":[74,94,119,140],"quantization-aware":[75],"training":[76],"(QAT)":[77],"To":[80],"mitigate":[81],"issue":[83],"prompting":[85],"node":[87],"alone":[89],"can":[90],"only":[91],"make":[92],"part":[93],"quantized":[96,120,142],"aggregation":[97],"result":[98],"optimal,":[99],"introduce":[101],"Low-Rank":[102],"Aggregation":[103],"Prompting":[104],"(LoRAP),":[105],"injects":[107],"lightweight,":[108],"input-dependent":[109],"prompts":[110],"into":[111],"each":[112],"aggregated":[113],"feature":[114],"optimize":[116],"results":[118],"aggregations.":[121],"Extensive":[122],"evaluations":[123],"on":[124],"4":[125],"leading":[126],"QAT":[127],"frameworks":[128],"over":[129],"9":[130],"datasets":[132],"demonstrate":[133],"LoRAP":[135],"consistently":[136],"enhances":[137],"low-bit":[141],"GNNs":[143],"while":[144],"introducing":[145],"minimal":[147],"computational":[148],"overhead.":[149]},"counts_by_year":[],"updated_date":"2026-01-23T23:24:52.574035","created_date":"2026-01-23T00:00:00"}