{"id":"https://openalex.org/W7224129461","doi":"https://doi.org/10.48550/arxiv.2610.37450","title":"Graph Representation Learning via Adaptive Expectile Aggregation","display_name":"Graph Representation Learning via Adaptive Expectile Aggregation","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224129461","doi":"https://doi.org/10.48550/arxiv.2610.37450"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.37450","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37450","pdf_url":"https://arxiv.org/pdf/2610.37450","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.37450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135995055","display_name":"Tianyi Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Tianyi","raw_affiliation_strings":["Department of Statistics , Colorado State University Fort Collins , CO 80523 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , Colorado State University Fort Collins , CO 80523 , USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160034238","display_name":"Wei Lan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan, Wei","raw_affiliation_strings":["Laboratory for Data Intelligence and Innovation in Finance and Economics and Center of Statistical Research Southwestern University of Finance and Economics , Chengdu , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Data Intelligence and Innovation in Finance and Economics and Center of Statistical Research Southwestern University of Finance and Economics , Chengdu , China","institution_ids":["https://openalex.org/I204831749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.0,"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/graph-neural-networks","display_name":"graph neural networks","score":0.949999988079071},{"id":"https://openalex.org/keywords/neighborhood-aggregation","display_name":"neighborhood aggregation","score":0.8849999904632568},{"id":"https://openalex.org/keywords/heterophilic-graphs","display_name":"heterophilic graphs","score":0.9269999861717224},{"id":"https://openalex.org/keywords/mean-aggregation","display_name":"mean aggregation","score":0.5590000152587891},{"id":"https://openalex.org/keywords/fixed-point-iteration","display_name":"fixed point iteration","score":0.5509999990463257}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4853000044822693},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44440001249313354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4293999969959259},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.42910000681877136},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.32420000433921814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C137345334","wikidata":"https://www.wikidata.org/wiki/Q7303350","display_name":"Recursive partitioning","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.37450","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37450","pdf_url":"https://arxiv.org/pdf/2610.37450","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.37450","doi":"https://doi.org/10.48550/arxiv.2610.37450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.37450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.37450","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37450","pdf_url":"https://arxiv.org/pdf/2610.37450","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G150437932","display_name":null,"funder_award_id":"72422020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6037768184","display_name":null,"funder_award_id":"72333001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8980066618","display_name":null,"funder_award_id":"12531011","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"},{"id":"https://openalex.org/F4320329795","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224129461.pdf","grobid_xml":"https://content.openalex.org/works/W7224129461.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4377000456","https://openalex.org/W4221148461","https://openalex.org/W7080776754","https://openalex.org/W4402273915","https://openalex.org/W4411551771","https://openalex.org/W4402029670","https://openalex.org/W3036490401","https://openalex.org/W2993822271","https://openalex.org/W3172682261","https://openalex.org/W7136083644"],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"rely":[4],"critically":[5],"on":[6,67,142],"neighborhood":[7,40,95],"aggregation,":[8],"yet":[9],"conventional":[10],"mean":[11,57,116],"aggregation":[12,30,50,58,104],"may":[13],"fail":[14],"to":[15,38,110],"capture":[16,39],"class-relevant":[17],"distributional":[18],"information,":[19],"particularly":[20],"in":[21,135],"heterophilic":[22,94,145],"graphs.":[23],"We":[24,87],"propose":[25],"ExpectileGCN,":[26],"an":[27],"adaptive":[28],"graph":[29],"framework":[31],"that":[32,102,130],"introduces":[33],"a":[34,60,112,119],"learnable":[35],"expectile":[36,103],"level":[37],"information":[41],"beyond":[42],"the":[43],"mean.":[44],"The":[45],"proposed":[46],"operator":[47],"continuously":[48],"adjusts":[49],"between":[51],"minimum-":[52],"and":[53,70,81,144,152,158],"maximum-type":[54],"behaviors,":[55],"with":[56,123],"as":[59],"special":[61],"case.":[62],"A":[63],"differentiable":[64],"approximation":[65],"based":[66],"sigmoid":[68],"smoothing":[69],"fixed-point":[71],"iterations":[72],"enables":[73],"end-to-end":[74],"optimization.":[75],"Theoretically,":[76],"we":[77,100,128],"establish":[78,129],"stability":[79],"properties":[80],"transductive":[82],"generalization":[83],"guarantees":[84],"for":[85],"ExpectileGCN.":[86],"further":[88],"investigate":[89],"its":[90],"classification":[91,113,139],"risk":[92],"under":[93,155],"models.":[96],"For":[97],"informative":[98],"neighborhoods,":[99],"show":[101],"can":[105,133],"exploit":[106],"class-dependent":[107],"scale":[108],"differences":[109],"achieve":[111],"advantage":[114,132],"over":[115],"aggregation.":[117],"Under":[118],"local":[120],"asymptotic":[121],"regime":[122],"diminishing":[124],"per-neighbor":[125],"label":[126],"informativeness,":[127],"this":[131],"persist":[134],"terms":[136],"of":[137],"limiting":[138],"risk.":[140],"Experiments":[141],"homophilic":[143],"benchmark":[146],"graphs":[147],"demonstrate":[148],"strong":[149],"predictive":[150],"performance":[151],"improved":[153],"robustness":[154],"feature":[156],"corruption":[157],"structural":[159],"perturbations.":[160]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-29T00:00:00"}