{"id":"https://openalex.org/W4417262889","doi":"https://doi.org/10.1109/isqed69900.2026.11534669","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","display_name":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W4417262889","doi":"https://doi.org/10.1109/isqed69900.2026.11534669"},"language":"en","primary_location":{"id":"doi:10.1109/isqed69900.2026.11534669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed69900.2026.11534669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 27th International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.18804","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028417807","display_name":"Wencheng Zou","orcid":"https://orcid.org/0000-0001-8324-2600"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wencheng Zou","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065262986","display_name":"Nan Wu","orcid":"https://orcid.org/0000-0001-8291-4292"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Wu","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02120686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.3837999999523163,"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":0.3837999999523163,"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":0.15379999577999115,"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":0.0820000022649765,"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/robustness","display_name":"Robustness (evolution)","score":0.7646999955177307},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6018000245094299},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4977000057697296},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.44530001282691956},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3828999996185303},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.375900000333786},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.3215999901294708}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7646999955177307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376999855041504},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5698000192642212},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.44530001282691956},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402000069618225},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C97042676","wikidata":"https://www.wikidata.org/wiki/Q5597097","display_name":"Graph reduction","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/isqed69900.2026.11534669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed69900.2026.11534669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 27th International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.18804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18804","pdf_url":"https://arxiv.org/pdf/2507.18804","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.18804","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.18804","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.18804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18804","pdf_url":"https://arxiv.org/pdf/2507.18804","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"are":[4],"increasingly":[5],"deployed":[6],"in":[7],"safety-critical":[8],"domains":[9],"such":[10,63],"as":[11,68],"finance":[12],"and":[13,40,57,76,85,104,109,138,141],"healthcare,":[14],"where":[15],"erroneous":[16],"predictions":[17],"can":[18],"have":[19,28],"severe":[20],"consequences.":[21],"While":[22],"prior":[23],"studies":[24],"on":[25,31],"GNN":[26,90,133],"robustness":[27,130],"primarily":[29],"focused":[30],"software-level":[32],"threats,":[33],"hardware-induced":[34],"faults,":[35],"particularly":[36],"transient":[37],"bit":[38],"flips":[39],"silent":[41],"data":[42],"corruption,":[43],"remain":[44],"underexplored.":[45],"As":[46],"hardware":[47],"systems":[48],"scale":[49],"to":[50,54,62,66,88,92,100,118,149],"advanced":[51],"technology":[52,72],"nodes":[53],"meet":[55],"performance":[56,147],"energy":[58],"demands,":[59],"their":[60],"vulnerability":[61],"faults":[64],"continues":[65],"grow,":[67],"reported":[69],"by":[70],"major":[71],"companies":[73],"including":[74],"Google":[75],"Meta.":[77],"In":[78],"response,":[79],"we":[80],"propose":[81],"Ralts,":[82],"a":[83],"generalizable":[84],"lightweight":[86],"solution":[87],"bolster":[89],"resilience":[91],"bit-flip":[93],"errors.":[94],"Ralts":[95,127,144,155],"exploits":[96],"graph":[97,107],"similarity":[98],"metrics":[99],"filter":[101],"out":[102],"outliers":[103],"recover":[105],"compromised":[106],"topology,":[108],"incorporates":[110],"these":[111],"protective":[112],"techniques":[113],"directly":[114],"into":[115],"aggregation":[116,153],"functions":[117],"support":[119],"any":[120],"message-passing":[121],"GNNs.":[122],"Evaluation":[123],"results":[124],"show":[125],"that":[126],"consistently":[128],"improves":[129],"across":[131],"diverse":[132],"models,":[134],"datasets,":[135],"error":[136],"patterns,":[137],"both":[139],"dense":[140],"sparse":[142],"architectures.":[143],"achieves":[145],"execution":[146],"comparable":[148],"native":[150],"PyTorch":[151],"Geometric":[152],"operators.":[154],"is":[156],"available":[157],"at:":[158],"https://github.com/ORCA-lab/Ralts.":[159]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}