{"id":"https://openalex.org/W4407953052","doi":"https://doi.org/10.1145/3701551.3703487","title":"Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation","display_name":"Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4407953052","doi":"https://doi.org/10.1145/3701551.3703487"},"language":"en","primary_location":{"id":"doi:10.1145/3701551.3703487","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701551.3703487","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 Eighteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3701551.3703487","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101894822","display_name":"Yoonhyuk Choi","orcid":"https://orcid.org/0000-0003-4359-5596"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yoonhyuk Choi","raw_affiliation_strings":["Samsung, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081493283","display_name":"Jiho Choi","orcid":"https://orcid.org/0000-0002-7140-7962"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiho Choi","raw_affiliation_strings":["KAIST, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079020226","display_name":"Taewook Ko","orcid":"https://orcid.org/0000-0001-7248-4751"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taewook Ko","raw_affiliation_strings":["Samsung, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015798913","display_name":"Chong-kwon Kim","orcid":"https://orcid.org/0000-0002-9492-6546"},"institutions":[{"id":"https://openalex.org/I4210127102","display_name":"Korea Institute of Energy Research","ror":"https://ror.org/0298pes53","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210127102","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chong-Kwon Kim","raw_affiliation_strings":["Korea Institute of Energy Technology, Naju, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Institute of Energy Technology, Naju, Republic of Korea","institution_ids":["https://openalex.org/I4210127102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101894822"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":5.2247,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94324159,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"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":0.9995999932289124,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976000189781189,"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/overfitting","display_name":"Overfitting","score":0.8646860122680664},{"id":"https://openalex.org/keywords/hyperplane","display_name":"Hyperplane","score":0.7330532073974609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6302523612976074},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.531848669052124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5077767968177795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5064300298690796},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.5003273487091064},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44841518998146057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4074874520301819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3647766709327698},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31106194853782654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23985445499420166},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.16518986225128174},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06570705771446228}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8646860122680664},{"id":"https://openalex.org/C68693459","wikidata":"https://www.wikidata.org/wiki/Q657586","display_name":"Hyperplane","level":2,"score":0.7330532073974609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6302523612976074},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.531848669052124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5077767968177795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5064300298690796},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.5003273487091064},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44841518998146057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4074874520301819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3647766709327698},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31106194853782654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23985445499420166},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.16518986225128174},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06570705771446228},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701551.3703487","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701551.3703487","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 Eighteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701551.3703487","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701551.3703487","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 Eighteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.75,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2107559689","https://openalex.org/W2140619591","https://openalex.org/W2148489082","https://openalex.org/W2768755822","https://openalex.org/W2912636151","https://openalex.org/W2966461190","https://openalex.org/W2976859544","https://openalex.org/W2990138404","https://openalex.org/W3083272131","https://openalex.org/W3093814892","https://openalex.org/W3095746859","https://openalex.org/W3100646853","https://openalex.org/W3114928288","https://openalex.org/W3116239416","https://openalex.org/W3133744637","https://openalex.org/W3135696193","https://openalex.org/W3153880451","https://openalex.org/W3154503084","https://openalex.org/W3169350676","https://openalex.org/W3178330258","https://openalex.org/W3182165353","https://openalex.org/W3201087642","https://openalex.org/W3201888171","https://openalex.org/W3208238874","https://openalex.org/W3211600770","https://openalex.org/W4220848104","https://openalex.org/W4220900167","https://openalex.org/W4221144131","https://openalex.org/W4226087736","https://openalex.org/W4226183968","https://openalex.org/W4282942883","https://openalex.org/W4285302633","https://openalex.org/W4286892599","https://openalex.org/W4313639623","https://openalex.org/W4380520401","https://openalex.org/W4382203217","https://openalex.org/W4385992284","https://openalex.org/W4387250121","https://openalex.org/W4393160468","https://openalex.org/W6600002382","https://openalex.org/W6770901814"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Message-passing":[0],"neural":[1],"networks":[2],"are":[3,14],"widely":[4],"employed":[5],"in":[6,57,131],"various":[7],"graph":[8],"mining":[9],"applications.":[10],"However,":[11],"these":[12,70],"methods":[13],"susceptible":[15],"to":[16,25,40,85],"the":[17,43,52,58,63,86,90],"scarcity":[18],"of":[19,45,54],"labeled":[20],"data,":[21],"which":[22],"often":[23],"leads":[24],"overfitting.":[26],"Our":[27],"observations":[28],"suggest":[29],"that":[30,82,101,123],"sparse":[31],"initial":[32,59,87],"vectors":[33],"further":[34],"exacerbate":[35],"this":[36,74,109],"issue":[37],"by":[38],"failing":[39],"fully":[41],"represent":[42],"range":[44],"learnable":[46],"parameters.":[47,71],"This":[48],"sparsity":[49],"can":[50],"hinder":[51],"optimization":[53],"specific":[55],"dimensions":[56],"projection":[60,91],"matrix,":[61],"as":[62],"training":[64],"samples":[65],"may":[66],"not":[67],"adequately":[68],"span":[69],"To":[72],"overcome":[73],"challenge,":[75],"we":[76,99],"propose":[77],"a":[78,104],"novel":[79],"perturbation":[80,115],"technique":[81,125],"introduces":[83],"variability":[84],"features":[88],"and":[89],"hyperplane.":[92],"Notably,":[93],"even":[94],"without":[95],"employing":[96],"grid":[97],"search,":[98],"demonstrate":[100],"shifting":[102],"with":[103],"small":[105],"estimated":[106],"value":[107],"mitigates":[108],"problem":[110],"more":[111],"effectively":[112],"than":[113],"other":[114],"methods.":[116],"Experimental":[117],"results":[118],"on":[119],"real-world":[120],"datasets":[121],"reveal":[122],"our":[124],"significantly":[126],"enhances":[127],"node":[128],"classification":[129],"accuracy":[130],"semi-supervised":[132],"scenarios.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}