{"id":"https://openalex.org/W4310627533","doi":"https://doi.org/10.48550/arxiv.2212.00024","title":"Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation","display_name":"Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation","publication_year":2022,"publication_date":"2022-11-30","ids":{"openalex":"https://openalex.org/W4310627533","doi":"https://doi.org/10.48550/arxiv.2212.00024"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2212.00024","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.00024","pdf_url":"https://arxiv.org/pdf/2212.00024","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.00024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100383083","display_name":"Ying Chen","orcid":"https://orcid.org/0000-0002-7546-3822"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Ying","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068323131","display_name":"Siwei Qiang","orcid":"https://orcid.org/0000-0003-1625-4366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang, Siwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085117395","display_name":"Mingming Ha","orcid":"https://orcid.org/0000-0002-2901-9608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ha, Mingming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442746","display_name":"Xiaolei Liu","orcid":"https://orcid.org/0000-0002-7082-641X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaolei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032783414","display_name":"Shaoshuai Li","orcid":"https://orcid.org/0000-0003-2949-668X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shaoshuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050391202","display_name":"Lingfeng Yuan","orcid":"https://orcid.org/0009-0006-4107-5801"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Lingfeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750075","display_name":"Xiaobo Guo","orcid":"https://orcid.org/0000-0002-6817-626X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xiaobo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101867605","display_name":"Zhenfeng Zhu","orcid":"https://orcid.org/0000-0001-7315-3276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhenfeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100383083"],"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":0.9711999893188477,"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":0.9711999893188477,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.9380000233650208,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9326000213623047,"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/computer-science","display_name":"Computer science","score":0.6387776136398315},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.554804265499115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5526849627494812},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48522260785102844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3661186397075653},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35242658853530884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387776136398315},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.554804265499115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5526849627494812},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48522260785102844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3661186397075653},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35242658853530884}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2212.00024","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.00024","pdf_url":"https://arxiv.org/pdf/2212.00024","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2212.00024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.00024","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.00024","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.00024","pdf_url":"https://arxiv.org/pdf/2212.00024","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4310627533.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W1926736923","https://openalex.org/W2942177010"],"abstract_inverted_index":{"In":[0,193],"recent":[1],"years,":[2],"semi-supervised":[3],"graph":[4,37],"learning":[5],"with":[6,26,105],"data":[7,185],"augmentation":[8,122],"(DA)":[9],"is":[10,72,135,207,231],"currently":[11],"the":[12,54,65,75,81,111,127,140,149,165,170,175,180,187,198,205,241],"most":[13],"commonly":[14],"used":[15],"and":[16,62,84,120,146,159,168,186,218,248,251,256],"best-performing":[17],"method":[18,99],"to":[19,47,64,163,195,233,243],"enhance":[20],"model":[21],"robustness":[22],"in":[23,35,87,117,236],"sparse":[24],"scenarios":[25],"few":[27],"labeled":[28,184],"samples.":[29],"Differing":[30],"from":[31],"homogeneous":[32],"graph,":[33],"DA":[34,45,203],"heterogeneous":[36,50,130],"has":[38],"greater":[39],"challenges:":[40],"heterogeneity":[41,114],"of":[42,57,60,70,113,115,129,139,151,153,172,179,201],"information":[43,55,71,116],"requires":[44],"strategies":[46,123],"effectively":[48,196],"handle":[49],"relations,":[51],"which":[52],"considers":[53],"contribution":[56],"different":[58],"types":[59],"neighbors":[61],"edges":[63],"target":[66],"nodes.":[67],"Furthermore,":[68],"over-squashing":[69,152],"caused":[73],"by":[74,80,253],"negative":[76,166],"curvature":[77,167],"that":[78,223],"formed":[79],"non-uniformity":[82],"distribution":[83],"strong":[85],"clustering":[86],"complex":[88],"graph.":[89,131],"To":[90],"address":[91],"these":[92],"challenges,":[93],"this":[94],"paper":[95],"presents":[96],"a":[97],"novel":[98],"named":[100],"Semi-Supervised":[101],"Heterogeneous":[102],"Graph":[103],"Learning":[104],"Multi-level":[106],"Data":[107],"Augmentation":[108],"(HG-MDA).":[109],"For":[110,148],"problem":[112,150],"DA,":[118],"node":[119],"topology":[121],"are":[124,161],"proposed":[125],"for":[126,142,183,190],"characteristics":[128],"And":[132],"meta-relation-based":[133],"attention":[134],"applied":[136,232],"as":[137],"one":[138],"indexes":[141],"selecting":[143],"augmented":[144],"nodes":[145],"edges.":[147],"information,":[154],"triangle":[155],"based":[156],"edge":[157],"adding":[158],"removing":[160],"designed":[162],"alleviate":[164],"bring":[169],"gain":[171],"topology.":[173],"Finally,":[174],"loss":[176,182],"function":[177],"consists":[178],"cross-entropy":[181],"consistency":[188],"regularization":[189],"unlabeled":[191],"data.":[192],"order":[194],"fuse":[197],"prediction":[199],"results":[200],"various":[202],"strategies,":[204],"sharpening":[206],"used.":[208],"Existing":[209],"experiments":[210],"on":[211],"public":[212],"datasets,":[213],"i.e.,":[214],"ACM,":[215],"DBLP,":[216],"OGB,":[217],"industry":[219],"dataset":[220],"MB":[221],"show":[222],"HG-MDA":[224,230],"outperforms":[225],"current":[226],"SOTA":[227],"models.":[228],"Additionly,":[229],"user":[234],"identification":[235],"internet":[237],"finance":[238],"scenarios,":[239],"helping":[240],"business":[242],"add":[244],"30%":[245],"key":[246],"users,":[247],"increase":[249],"loans":[250],"balances":[252],"3.6%,":[254],"11.1%,":[255],"9.8%.":[257]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}