{"id":"https://openalex.org/W4415540863","doi":"https://doi.org/10.1145/3746027.3754822","title":"Towards Effective Open-set Graph Class-incremental Learning","display_name":"Towards Effective Open-set Graph Class-incremental Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540863","doi":"https://doi.org/10.1145/3746027.3754822"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754822","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754822","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080052330","display_name":"Jiazhen Chen","orcid":"https://orcid.org/0000-0001-9962-2974"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jiazhen Chen","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109302101","display_name":"Zheng Ma","orcid":"https://orcid.org/0009-0005-6449-5983"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zheng Ma","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028372795","display_name":"Sichao Fu","orcid":"https://orcid.org/0000-0002-4363-1000"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sichao Fu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046114637","display_name":"Mingbin Feng","orcid":"https://orcid.org/0000-0002-9748-6435"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mingbin Feng","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053070980","display_name":"Tony S. Wirjanto","orcid":"https://orcid.org/0000-0003-1324-9131"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tony S. Wirjanto","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028245257","display_name":"Weihua Ou","orcid":"https://orcid.org/0000-0001-5241-7703"},"institutions":[{"id":"https://openalex.org/I154893126","display_name":"Guizhou Normal University","ror":"https://ror.org/02x1pa065","country_code":"CN","type":"education","lineage":["https://openalex.org/I154893126"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua Ou","raw_affiliation_strings":["Guizhou Normal University, Guiyang, Guizhou, China"],"affiliations":[{"raw_affiliation_string":"Guizhou Normal University, Guiyang, Guizhou, China","institution_ids":["https://openalex.org/I154893126"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5080052330"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17093049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11956","last_page":"11965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T12676","display_name":"Machine Learning and ELM","score":0.992900013923645,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9132000207901001,"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/forgetting","display_name":"Forgetting","score":0.6453999876976013},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.572700023651123},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5347999930381775},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5076000094413757},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4239000082015991},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.41929998993873596},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.38029998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046999931335449},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6453999876976013},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425000190734863},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5076000094413757},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4810999929904938},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.3375999927520752},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2791999876499176}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754822","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754822","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2026106228","https://openalex.org/W2560647685","https://openalex.org/W2904509905","https://openalex.org/W2963149653","https://openalex.org/W2963875483","https://openalex.org/W3002924435","https://openalex.org/W3110791298","https://openalex.org/W3127228978","https://openalex.org/W3164709496","https://openalex.org/W3215627852","https://openalex.org/W4319054544"],"related_works":[],"abstract_inverted_index":{"Graphs":[0],"play":[1],"a":[2,53,93,133,159,187,248],"pivotal":[3],"role":[4],"in":[5,73],"multimedia":[6],"applications":[7],"by":[8,35],"integrating":[9],"information":[10],"to":[11,28,30,62,64,144,166,190,215],"model":[12],"complex":[13],"relationships.":[14],"Recently,":[15],"graph":[16,24,32,97,179],"class-incremental":[17,98],"learning":[18,37,99],"(GCIL)":[19],"has":[20],"garnered":[21],"attention,":[22],"allowing":[23],"neural":[25],"networks":[26],"(GNNs)":[27],"adapt":[29],"evolving":[31],"analytical":[33],"tasks":[34],"incrementally":[36],"new":[38],"class":[39,218],"knowledge":[40,43,174],"while":[41,220],"retaining":[42],"of":[44,107,114,125,153,226,260],"old":[45,108,171],"classes.":[46,67,155],"Existing":[47],"GCIL":[48,264],"methods":[49],"primarily":[50],"focus":[51],"on":[52,254],"closed-set":[54],"assumption,":[55],"where":[56,76],"all":[57,228],"test":[58],"samples":[59,194,230],"are":[60,84],"presumed":[61],"belong":[63],"previously":[65],"known":[66],"Such":[68],"assumption":[69],"restricts":[70],"their":[71,216],"applicability":[72],"real-world":[74],"scenarios,":[75],"unknown":[77,115,154,183,229],"classes":[78],"naturally":[79],"emerge":[80],"during":[81,86],"inference,":[82],"and":[83,117,149,198,265],"absent":[85],"training.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91,185],"explore":[92],"more":[94],"challenging":[95],"open-set":[96,119,250,266],"scenario":[100],"with":[101],"two":[102],"intertwined":[103],"challenges:":[104],"catastrophic":[105,147],"forgetting":[106,148],"classes,":[109,116,172,184],"which":[110,121,139,211],"impairs":[111],"the":[112,123,130,258],"detection":[113,152],"inadequate":[118],"recognition,":[120],"destabilizes":[122],"retention":[124],"learned":[126],"knowledge.":[127],"To":[128,156,181],"address":[129],"above":[131],"problems,":[132],"novel":[134,203],"OGCIL":[135,261],"framework":[136],"is":[137,164,208],"proposed,":[138,210],"utilizes":[140],"pseudo-sample":[141],"embedding":[142],"generation":[143],"effectively":[145],"mitigate":[146],"enable":[150],"robust":[151,249],"be":[157],"specific,":[158],"prototypical":[160,204],"conditional":[161],"variational":[162],"autoencoder":[163],"designed":[165],"synthesize":[167],"node":[168,200],"embeddings":[169,214,223],"for":[170],"enabling":[173],"replay":[175],"without":[176],"storing":[177],"raw":[178],"data.":[180],"handle":[182],"employ":[186],"mixing-based":[188],"strategy":[189],"generate":[191],"out-of-distribution":[192],"(OOD)":[193],"from":[195],"pseudo":[196],"in-distribution":[197,213],"current":[199],"embeddings.":[201],"A":[202],"hypersphere":[205],"classification":[206],"loss":[207],"further":[209],"anchors":[212],"respective":[217],"prototypes,":[219],"repelling":[221],"OOD":[222],"away.":[224],"Instead":[225],"assigning":[227],"into":[231],"one":[232],"cluster,":[233],"our":[234],"proposed":[235],"objective":[236],"function":[237],"explicitly":[238],"models":[239],"them":[240],"as":[241],"outliers":[242],"through":[243],"prototype-aware":[244],"rejection":[245],"regions,":[246],"ensuring":[247],"recognition.":[251],"Extensive":[252],"experiments":[253],"five":[255],"benchmarks":[256],"demonstrate":[257],"effectiveness":[259],"over":[262],"existing":[263],"GNN":[267],"methods.":[268]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}