{"id":"https://openalex.org/W3116239416","doi":"https://doi.org/10.1145/3437963.3441734","title":"Learning to Drop: Robust Graph Neural Network via Topological Denoising","display_name":"Learning to Drop: Robust Graph Neural Network via Topological Denoising","publication_year":2021,"publication_date":"2021-03-06","ids":{"openalex":"https://openalex.org/W3116239416","doi":"https://doi.org/10.1145/3437963.3441734","mag":"3116239416"},"language":"en","primary_location":{"id":"doi:10.1145/3437963.3441734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5102761357","display_name":"Dongsheng Luo","orcid":"https://orcid.org/0000-0003-4192-0826"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongsheng Luo","raw_affiliation_strings":["Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037724644","display_name":"Wei Cheng","orcid":"https://orcid.org/0000-0001-5456-626X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Cheng","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210504","display_name":"Wenchao Yu","orcid":"https://orcid.org/0000-0002-2480-448X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenchao Yu","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091340586","display_name":"Bo Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Zong","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043236347","display_name":"Jingchao Ni","orcid":"https://orcid.org/0000-0002-2986-6612"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingchao Ni","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047926894","display_name":"Haifeng Chen","orcid":"https://orcid.org/0000-0002-7740-1510"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haifeng Chen","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060725887","display_name":"X. D. Zhang","orcid":"https://orcid.org/0000-0003-0940-6595"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Zhang","raw_affiliation_strings":["Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102761357"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":23.5082,"has_fulltext":false,"cited_by_count":235,"citation_normalized_percentile":{"value":0.99634345,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"779","last_page":"787"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"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":0.9998999834060669,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6637447476387024},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44346296787261963},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4402436316013336},{"id":"https://openalex.org/keywords/topological-graph-theory","display_name":"Topological graph theory","score":0.4194554090499878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4102681875228882},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37666499614715576},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32078516483306885},{"id":"https://openalex.org/keywords/voltage-graph","display_name":"Voltage graph","score":0.1466170847415924},{"id":"https://openalex.org/keywords/line-graph","display_name":"Line graph","score":0.13423588871955872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6637447476387024},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44346296787261963},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4402436316013336},{"id":"https://openalex.org/C157406716","wikidata":"https://www.wikidata.org/wiki/Q4115842","display_name":"Topological graph theory","level":5,"score":0.4194554090499878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4102681875228882},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37666499614715576},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32078516483306885},{"id":"https://openalex.org/C22149727","wikidata":"https://www.wikidata.org/wiki/Q7940747","display_name":"Voltage graph","level":4,"score":0.1466170847415924},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.13423588871955872}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437963.3441734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2686447995","display_name":null,"funder_award_id":"IIS-1707548,CBET-1638320","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1501856433","https://openalex.org/W1512387364","https://openalex.org/W2059076129","https://openalex.org/W2093184664","https://openalex.org/W2116341502","https://openalex.org/W2139391136","https://openalex.org/W2156512439","https://openalex.org/W2167844587","https://openalex.org/W2204257188","https://openalex.org/W2468907370","https://openalex.org/W2624431344","https://openalex.org/W2922517354","https://openalex.org/W2945420892","https://openalex.org/W2963725088","https://openalex.org/W2964051675","https://openalex.org/W2964173611","https://openalex.org/W2970316566","https://openalex.org/W2970986190","https://openalex.org/W2994872359","https://openalex.org/W2994968268","https://openalex.org/W2996084050","https://openalex.org/W2997079913","https://openalex.org/W2998122931","https://openalex.org/W4248241950","https://openalex.org/W6677316912"],"related_works":["https://openalex.org/W4205991736","https://openalex.org/W2767597557","https://openalex.org/W3094552683","https://openalex.org/W3211302945","https://openalex.org/W4284975088","https://openalex.org/W4366772049","https://openalex.org/W4386136067","https://openalex.org/W4388486485","https://openalex.org/W4311211767","https://openalex.org/W4387415041"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"shown":[5],"to":[6,17,40,59,79,90,127,151],"be":[7,142],"powerful":[8],"tools":[9],"for":[10,137,189],"graph":[11,107,136],"analytics.":[12],"The":[13],"key":[14,146],"idea":[15],"is":[16,125],"recursively":[18],"propagate":[19],"and":[20,52,83,162,170,183],"aggregate":[21],"information":[22],"along":[23],"the":[24,27,34,41,44,64,81,100,105,115,118,121,129,133,178,184],"edges":[25,97,103],"of":[26,43,86,102,117,180],"given":[28],"graph.":[29,46],"Despite":[30],"their":[31,153],"success,":[32],"however,":[33],"existing":[35],"GNNs":[36,87,181],"are":[37,49],"usually":[38],"sensitive":[39],"quality":[42],"input":[45],"Real-world":[47],"graphs":[48],"often":[50],"noisy":[51,191],"contain":[53],"task-irrelevant":[54,92,96],"edges,":[55],"which":[56],"may":[57],"lead":[58],"suboptimal":[60],"generalization":[61,84],"performance":[62,85,179,185],"in":[63,104,148],"learned":[65],"GNN":[66,149],"models.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"propose":[72],"PTDNet,":[73],"a":[74,145],"parameterized":[75,109],"topological":[76],"denoising":[77],"network,":[78],"improve":[80,152,177],"robustness":[82],"by":[88,98],"learning":[89],"drop":[91],"edges.":[93],"PTDNet":[94,140,175],"prunes":[95],"penalizing":[99],"number":[101],"sparsified":[106,135],"with":[108],"networks.":[110],"To":[111],"take":[112],"into":[113],"consideration":[114],"topology":[116],"entire":[119],"graph,":[120],"nuclear":[122],"norm":[123],"regularization":[124],"applied":[126],"impose":[128],"low-rank":[130],"constraint":[131],"on":[132,155,167],"resulting":[134],"better":[138],"generalization.":[139],"can":[141,176],"used":[143],"as":[144,159],"component":[147],"models":[150],"performances":[154],"various":[156],"tasks,":[157],"such":[158],"node":[160],"classification":[161],"link":[163],"prediction.":[164],"Experimental":[165],"studies":[166],"both":[168],"synthetic":[169],"benchmark":[171],"datasets":[172],"show":[173],"that":[174],"significantly":[182],"gain":[186],"becomes":[187],"larger":[188],"more":[190],"datasets.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":60},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}