{"id":"https://openalex.org/W4414982779","doi":"https://doi.org/10.1109/tpami.2025.3618329","title":"Layer-Adaptive-Augmentation-Based Graph Contrastive Learning With Feature Decorrelation","display_name":"Layer-Adaptive-Augmentation-Based Graph Contrastive Learning With Feature Decorrelation","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414982779","doi":"https://doi.org/10.1109/tpami.2025.3618329","pmid":"https://pubmed.ncbi.nlm.nih.gov/41056169"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3618329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3618329","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5015248791","display_name":"Yuhua Xu","orcid":"https://orcid.org/0000-0001-9430-8791"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhua Xu","raw_affiliation_strings":["School of Information and Intelligent Science, Donghua University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9430-8791","affiliations":[{"raw_affiliation_string":"School of Information and Intelligent Science, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345552","display_name":"Junli Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junli Wang","raw_affiliation_strings":["Key Laboratory of Embedded System and Service Computing (Tongji University), Ministry of Education, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7185-9731","affiliations":[{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Tongji University), Ministry of Education, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Duan","orcid":"https://orcid.org/0009-0002-3558-3085"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Duan","raw_affiliation_strings":["College of Computer Science and Cyber Engineering, Guangzhou University, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0002-3558-3085","affiliations":[{"raw_affiliation_string":"College of Computer Science and Cyber Engineering, Guangzhou University, Guangdong, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066099338","display_name":"Changjun Jiang","orcid":"https://orcid.org/0000-0003-0637-9317"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjun Jiang","raw_affiliation_strings":["Key Laboratory of Embedded System and Service Computing (Tongji University), Ministry of Education, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0637-9317","affiliations":[{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Tongji University), Ministry of Education, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015248791"],"corresponding_institution_ids":["https://openalex.org/I181326427"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14081931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"2","first_page":"1750","last_page":"1761"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9824000000953674,"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":0.9824000000953674,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9147999882698059,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5339000225067139},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.527400016784668},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5044000148773193},{"id":"https://openalex.org/keywords/decorrelation","display_name":"Decorrelation","score":0.4343999922275543},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4074000120162964},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3928000032901764},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39010000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6148999929428101},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2776800370","wikidata":"https://www.wikidata.org/wiki/Q5172864","display_name":"Correlative","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3618329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3618329","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41056169","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41056169","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2300031476","display_name":null,"funder_award_id":"2232025D-36","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1577841048","https://openalex.org/W2008857988","https://openalex.org/W2092750499","https://openalex.org/W2097308346","https://openalex.org/W2099438806","https://openalex.org/W2808803559","https://openalex.org/W2962756421","https://openalex.org/W3129850062","https://openalex.org/W3185645213","https://openalex.org/W3190214286","https://openalex.org/W4221023051","https://openalex.org/W4282975557","https://openalex.org/W4321206894","https://openalex.org/W4323065138","https://openalex.org/W4381786098","https://openalex.org/W4386634632","https://openalex.org/W4389328404","https://openalex.org/W4392796768","https://openalex.org/W4394828332","https://openalex.org/W4394966906","https://openalex.org/W4396757514","https://openalex.org/W4400581069","https://openalex.org/W4403524910","https://openalex.org/W4409363443","https://openalex.org/W4409364207","https://openalex.org/W4411055446","https://openalex.org/W4415796503"],"related_works":[],"abstract_inverted_index":{"Graph":[0,86],"Contrastive":[1,87],"Learning":[2,88],"(GCL)":[3],"methods":[4,29],"typically":[5],"leverage":[6],"augmentation":[7,98],"techniques":[8],"to":[9,54,148],"generate":[10],"different":[11,139],"graph":[12,165,172],"views":[13],"for":[14,20,42],"comparison,":[15],"thereby":[16],"learning":[17],"corresponding":[18],"representations":[19,69,133],"graph-related":[21],"tasks":[22],"in":[23],"label-scarce":[24],"scenarios.":[25],"However,":[26],"existing":[27],"GCL":[28],"suffer":[30],"from":[31],"two":[32],"primary":[33],"limitations:":[34],"1)":[35],"they":[36],"use":[37],"predefined":[38],"or":[39,179],"one-time":[40],"perturbations":[41,102],"augmentation,":[43],"ignoring":[44],"adaptive":[45,97],"noise":[46],"injection":[47],"during":[48],"forward":[49],"propagation":[50],"and":[51,110,134,151],"thus":[52],"leading":[53],"suboptimal":[55],"model":[56,116,147],"robustness;":[57],"2)":[58],"their":[59],"contrast":[60],"mechanisms":[61],"mainly":[62],"focus":[63],"on":[64,170],"the":[65,72,94,105,129,135,146,158,164],"agreement":[66,130],"of":[67,160,186],"inter-graph":[68],"while":[70,103],"neglecting":[71],"dimensional":[73],"feature":[74,90,136],"redundancy":[75],"within":[76,141],"intra-graph":[77],"representations.":[78,154],"To":[79],"solve":[80],"these":[81],"issues,":[82],"we":[83,119,156],"propose":[84],"Layer-adaptive-augmentation-based":[85],"with":[89,183],"Decorrelation":[91],"(LGCLD).":[92],"First,":[93],"designed":[95],"layer-wise":[96],"method":[99],"performs":[100],"dynamic":[101],"maintaining":[104],"semantic":[106],"similarity":[107],"between":[108,131],"augmented":[109],"original":[111],"graphs,":[112],"which":[113],"can":[114],"improve":[115],"robustness.":[117],"Second,":[118],"introduce":[120],"an":[121],"Agreement-Decorrelation":[122],"loss":[123,162],"(AD":[124],"loss)":[125],"that":[126,175],"simultaneously":[127],"optimizes":[128],"graph-level":[132,143,153],"correlation":[137],"among":[138],"dimensions":[140],"each":[142],"representation,":[144],"promoting":[145],"learn":[149],"informative":[150],"non-redundant":[152],"Furthermore,":[155],"analyze":[157],"reasonableness":[159],"AD":[161],"through":[163],"information":[166],"bottleneck":[167],"principle.":[168],"Experiments":[169],"various-domain":[171],"datasets":[173],"demonstrate":[174],"LGCLD":[176],"achieves":[177],"better":[178],"competitive":[180],"performance":[181],"compared":[182],"a":[184],"series":[185],"state-of-the-art":[187],"baselines.":[188]},"counts_by_year":[],"updated_date":"2026-01-11T23:08:45.486102","created_date":"2025-10-10T00:00:00"}