{"id":"https://openalex.org/W7128482176","doi":"https://doi.org/10.48550/arxiv.2602.07708","title":"Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization","display_name":"Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization","publication_year":2026,"publication_date":"2026-02-07","ids":{"openalex":"https://openalex.org/W7128482176","doi":"https://doi.org/10.48550/arxiv.2602.07708"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.07708","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07708","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.07708","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125540198","display_name":"Ding Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125561097","display_name":"Siddharth Betala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Betala, Siddharth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125502133","display_name":"Chirag Agarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Chirag","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7166000008583069,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7166000008583069,"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":0.23549999296665192,"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":0.007300000172108412,"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/generalization","display_name":"Generalization","score":0.6725000143051147},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.5076000094413757},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4970000088214874},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4359999895095825},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4131999909877777},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4004000127315521}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6725000143051147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6261000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136999726295471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5511999726295471},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2928999960422516},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27149999141693115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.07708","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07708","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2602.07708","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07708","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Evaluating":[0],"the":[1,40,50,58,68,122],"quality":[2],"of":[3,23,61,70],"post-hoc":[4],"explanations":[5],"for":[6,121,147],"Graph":[7],"Neural":[8],"Networks":[9],"(GNNs)":[10],"remains":[11],"a":[12,54,97,118,144,159],"significant":[13],"challenge.":[14],"While":[15],"recent":[16],"years":[17],"have":[18],"seen":[19],"an":[20,37,77],"increasing":[21],"development":[22],"explainability":[24],"methods,":[25],"current":[26],"evaluation":[27],"metrics":[28],"(e.g.,":[29],"fidelity,":[30],"sparsity)":[31],"often":[32],"fail":[33],"to":[34,86,154,162],"assess":[35],"whether":[36],"explanation":[38,78],"identifies":[39],"true":[41,80],"underlying":[42],"causal":[43,59,81,124,156],"variables.":[44],"To":[45,92],"address":[46],"this,":[47,94],"we":[48,95],"propose":[49],"Explanation-Generalization":[51],"Score":[52],"(EGS),":[53],"metric":[55],"that":[56,75,99,141],"quantifies":[57],"relevance":[60],"GNN":[62],"explanations.":[63],"EGS":[64,142],"is":[65],"founded":[66],"on":[67,151],"principle":[69],"feature":[71],"invariance":[72],"and":[73,105,135],"posits":[74],"if":[76],"captures":[79],"drivers,":[82],"it":[83],"should":[84],"lead":[85],"stable":[87],"predictions":[88],"across":[89,133],"distribution":[90],"shifts.":[91],"quantify":[93],"introduce":[96],"framework":[98],"trains":[100],"GNNs":[101],"using":[102],"explanatory":[103],"subgraphs":[104],"evaluates":[106],"their":[107,152],"performance":[108],"in":[109],"Out-of-Distribution":[110],"(OOD)":[111],"settings":[112],"(here,":[113],"OOD":[114],"generalization":[115],"serves":[116],"as":[117],"rigorous":[119],"proxy":[120],"explanation's":[123],"validity).":[125],"Through":[126],"large-scale":[127],"validation":[128],"involving":[129],"11,200":[130],"model":[131],"combinations":[132],"synthetic":[134],"real-world":[136],"datasets,":[137],"our":[138],"results":[139],"demonstrate":[140],"provides":[143],"principled":[145],"benchmark":[146],"ranking":[148],"explainers":[149],"based":[150],"ability":[153],"capture":[155],"substructures,":[157],"offering":[158],"robust":[160],"alternative":[161],"traditional":[163],"fidelity-based":[164],"metrics.":[165]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-11T00:00:00"}