{"id":"https://openalex.org/W4412825866","doi":"https://doi.org/10.1145/3711896.3736947","title":"Explaining GNN Explanations with Edge Gradients","display_name":"Explaining GNN Explanations with Edge Gradients","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4412825866","doi":"https://doi.org/10.1145/3711896.3736947"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736947","doi":"https://doi.org/10.1145/3711896.3736947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736947","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3711896.3736947","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jesse He","orcid":"https://orcid.org/0009-0005-2622-6512","observed_orcids":["https://orcid.org/0009-0005-2622-6512"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse He","raw_affiliation_strings":["Hal\u0131c\u0131o\u011flu Data Science Institute, University of California, San Diego, San Diego, California, USA"],"raw_orcid":"https://orcid.org/0009-0005-2622-6512","affiliations":[{"raw_affiliation_string":"Hal\u0131c\u0131o\u011flu Data Science Institute, University of California, San Diego, San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037319191","display_name":"Akbar Rafiey","orcid":"https://orcid.org/0000-0003-1619-3997","observed_orcids":["https://orcid.org/0000-0003-1619-3997"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akbar Rafiey","raw_affiliation_strings":["Computer Science and Engineering, New York University, Brooklyn, New York, USA"],"raw_orcid":"https://orcid.org/0000-0003-1619-3997","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, New York University, Brooklyn, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075832074","display_name":"Gal Mishne","orcid":"https://orcid.org/0000-0002-5287-3626","observed_orcids":["https://orcid.org/0000-0002-5287-3626"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gal Mishne","raw_affiliation_strings":["Hal\u0131c\u0131o\u011flu Data Science Institute, University of California, San Diego, San Diego, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-5287-3626","affiliations":[{"raw_affiliation_string":"Hal\u0131c\u0131o\u011flu Data Science Institute, University of California, San Diego, San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101536052","display_name":"Yusu Wang","orcid":"https://orcid.org/0000-0001-7950-4348","observed_orcids":["https://orcid.org/0000-0001-7950-4348"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusu Wang","raw_affiliation_strings":["Hal\u0131c\u0131o\u011flu Data Science Institute, University of California, San Diego, San Diego, California, USA"],"raw_orcid":"https://orcid.org/0000-0001-7950-4348","affiliations":[{"raw_affiliation_string":"Hal\u0131c\u0131o\u011flu Data Science Institute, University of California, San Diego, San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.312,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93703876,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"884","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0,"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/graph-neural-networks","display_name":"graph neural networks","score":0.9369999766349792},{"id":"https://openalex.org/keywords/edge-gradient","display_name":"edge gradient","score":0.8569999933242798},{"id":"https://openalex.org/keywords/gnnexplainer","display_name":"GNNExplainer","score":0.9580000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5656169652938843},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5455110669136047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30893412232398987}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3711896.3736947","doi":"https://doi.org/10.1145/3711896.3736947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736947","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01048","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01048","pdf_url":"https://arxiv.org/pdf/2508.01048","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,"listed_in":[],"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":"pmh:oai:escholarship.org:ark:/13030/qt83t9f2hw","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/83t9f2hw","pdf_url":"https://escholarship.org/content/qt83t9f2hw/qt83t9f2hw.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PROCEEDINGS OF THE 31ST ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING V.2, KDD 2025","raw_type":"article"},{"id":"doi:10.48550/arxiv.2508.01048","doi":"https://doi.org/10.48550/arxiv.2508.01048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01048","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3711896.3736947","doi":"https://doi.org/10.1145/3711896.3736947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736947","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2081960379","display_name":null,"funder_award_id":"CCF-2217058, CCF-2112665, CCF-2403452, CCF-2310411","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G3416213352","display_name":"Collaborative Research: AF: Small: Graph Analysis: Integrating Metric and Topological Perspectives","funder_award_id":"2310411","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3744848179","display_name":"AI Institute for Learning-Enabled Optimization at Scale (TILOS)","funder_award_id":"2112665","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3818259406","display_name":"Collaborative Research: CIF: Medium:Data Manifolds and Local Geometry in Deep Networks","funder_award_id":"2403452","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3930916604","display_name":"Collaborative Research: EnCORE: Institute for Emerging CORE Methods in Data Science","funder_award_id":"2217058","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"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412825866.pdf","grobid_xml":"https://content.openalex.org/works/W4412825866.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1677182931","https://openalex.org/W1787224781","https://openalex.org/W2295107390","https://openalex.org/W2516809705","https://openalex.org/W2912083425","https://openalex.org/W2914304175","https://openalex.org/W2962858109","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2979481854","https://openalex.org/W3000120900","https://openalex.org/W3042313988","https://openalex.org/W3108823960","https://openalex.org/W3116637551","https://openalex.org/W3169325548","https://openalex.org/W4327813569","https://openalex.org/W4402778834","https://openalex.org/W6601955380","https://openalex.org/W6602680078"],"related_works":["https://openalex.org/W3210229802","https://openalex.org/W7170849521","https://openalex.org/W4399511754","https://openalex.org/W3116637551","https://openalex.org/W4288099617","https://openalex.org/W4404863529","https://openalex.org/W4396778400","https://openalex.org/W2970119293","https://openalex.org/W7130395028","https://openalex.org/W6929051383"],"abstract_inverted_index":{"In":[0,68,154],"recent":[1],"years,":[2],"the":[3,25,90,101,106,111,130,148,151,155],"remarkable":[4],"success":[5],"of":[6,18,63,89,100,150],"graph":[7],"neural":[8],"networks":[9],"(GNNs)":[10],"on":[11,45,147,184],"graph-structured":[12],"data":[13],"has":[14],"prompted":[15],"a":[16,58,73,143],"surge":[17],"methods":[19],"for":[20,27,38,57,169],"explaining":[21],"GNN":[22,28,48,65,77],"predictions.":[23],"However,":[24],"state-of-the-art":[26],"explainability":[29],"remains":[30],"in":[31,79,180],"flux.":[32],"Different":[33],"comparisons":[34],"find":[35],"mixed":[36],"results":[37,178],"different":[39,81],"methods,":[40,117],"with":[41,182],"many":[42],"explainers":[43],"struggling":[44],"more":[46,59],"complex":[47],"architectures":[49],"and":[50,93,114,187],"tasks.":[51],"This":[52],"presents":[53],"an":[54],"urgent":[55],"need":[56],"careful":[60],"theoretical":[61,108,177],"analysis":[62],"competing":[64],"explanation":[66],"methods.":[67,128],"this":[69],"work":[70],"we":[71,133,158,173],"take":[72],"closer":[74],"look":[75],"at":[76],"explanations":[78],"two":[80],"settings:":[82],"input-level":[83],"explanations,":[84,95],"which":[85,96,137],"produce":[86,97],"explanatory":[87,98],"subgraphs":[88,99],"input":[91,131],"graph,":[92],"layerwise":[94,156],"computation":[102],"graph.":[103],"We":[104],"establish":[105],"first":[107],"connections":[109,123],"between":[110,124],"popular":[112],"perturbation-based":[113],"classical":[115],"gradient-based":[116],"as":[118,120],"well":[119],"point":[121,159],"out":[122,160],"other":[125],"recently":[126],"proposed":[127],"At":[129],"level,":[132],"demonstrate":[134,174],"conditions":[135],"under":[136],"GNNExplainer":[138],"can":[139],"be":[140],"approximated":[141],"by":[142],"simple":[144],"heuristic":[145],"based":[146],"sign":[149],"edge":[152,162],"gradients.":[153],"setting,":[157],"that":[161],"gradients":[163],"are":[164],"equivalent":[165],"to":[166],"occlusion":[167],"search":[168],"linear":[170],"GNNs.":[171],"Finally,":[172],"how":[175],"our":[176],"manifest":[179],"practice":[181],"experiments":[183],"both":[185],"synthetic":[186],"real":[188],"datasets.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
