{"id":"https://openalex.org/W4224316369","doi":"https://doi.org/10.1145/3485447.3512155","title":"An Invertible Graph Diffusion Neural Network for Source Localization","display_name":"An Invertible Graph Diffusion Neural Network for Source Localization","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4224316369","doi":"https://doi.org/10.1145/3485447.3512155"},"language":"en","primary_location":{"id":"doi:10.1145/3485447.3512155","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3512155","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100619909","display_name":"Junxiang Wang","orcid":"https://orcid.org/0000-0002-6635-4296"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junxiang Wang","raw_affiliation_strings":["Computer Science, Emory University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Emory University, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083648576","display_name":"Junji Jiang","orcid":"https://orcid.org/0000-0001-9675-0903"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junji Jiang","raw_affiliation_strings":["Tianjin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048756500","display_name":"Liang Zhao","orcid":"https://orcid.org/0000-0002-2648-9989"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Zhao","raw_affiliation_strings":["Computer Science, Emory University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Emory University, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1058","last_page":"1069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9991999864578247,"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":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9933000206947327,"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":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7307755351066589},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.6324845552444458},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5360733866691589},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4982311725616455},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4893485903739929},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.45201051235198975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4451078772544861},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34097790718078613},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3382369875907898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307755351066589},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.6324845552444458},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5360733866691589},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4982311725616455},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4893485903739929},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.45201051235198975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4451078772544861},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34097790718078613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3382369875907898},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3485447.3512155","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3512155","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1669104078","https://openalex.org/W1954020979","https://openalex.org/W1970777322","https://openalex.org/W1977672204","https://openalex.org/W1981589225","https://openalex.org/W1992537918","https://openalex.org/W2094234423","https://openalex.org/W2095006675","https://openalex.org/W2121205191","https://openalex.org/W2127492100","https://openalex.org/W2143551222","https://openalex.org/W2150105124","https://openalex.org/W2162630660","https://openalex.org/W2509830164","https://openalex.org/W2528339895","https://openalex.org/W2605245004","https://openalex.org/W2740189214","https://openalex.org/W2743129938","https://openalex.org/W2748000169","https://openalex.org/W2767220239","https://openalex.org/W2767221212","https://openalex.org/W2788521628","https://openalex.org/W2789120929","https://openalex.org/W2799312619","https://openalex.org/W2809583854","https://openalex.org/W2819579046","https://openalex.org/W2902679889","https://openalex.org/W2903561442","https://openalex.org/W2903664715","https://openalex.org/W2907028664","https://openalex.org/W2907589687","https://openalex.org/W2908066257","https://openalex.org/W2912066479","https://openalex.org/W2912778443","https://openalex.org/W2921701073","https://openalex.org/W2927222677","https://openalex.org/W2951274548","https://openalex.org/W2954973878","https://openalex.org/W2963359731","https://openalex.org/W2963493749","https://openalex.org/W2971779724","https://openalex.org/W2976859544","https://openalex.org/W2983244957","https://openalex.org/W3001111845","https://openalex.org/W3012624334","https://openalex.org/W3028571922","https://openalex.org/W3048848247","https://openalex.org/W3113374047","https://openalex.org/W3116602816","https://openalex.org/W3153389197","https://openalex.org/W4206445139","https://openalex.org/W4289761690","https://openalex.org/W4293232152","https://openalex.org/W6747624847"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"Localizing":[0],"the":[1,19,31,46,93,102,131,187,190,238,241,247,250,284,293],"source":[2,23,98,150,199],"of":[3,45,78,104,144,189,207,240,249,256,286,292],"graph":[4,47,95,105,146,171,208,213,219],"diffusion":[5,48,147,172,220],"phenomena,":[6],"such":[7,69,84],"as":[8,85],"misinformation":[9],"propagation,":[10],"is":[11,53,61,75,100,108,116,280,296],"an":[12,180],"important":[13,62],"yet":[14],"extremely":[15],"challenging":[16],"task":[17],"in":[18,113,170,179,198],"real":[20],"world.":[21],"Existing":[22],"localization":[24,99,151],"models":[25,66,83,148,173,221],"typically":[26],"are":[27],"heavily":[28],"dependent":[29],"on":[30,81,152,301],"hand-crafted":[32],"rules":[33,71],"and":[34,127,193,196],"only":[35],"tailored":[36],"for":[37,50,67,90,149,174],"certain":[38],"domain-specific":[39],"applications.":[40],"Unfortunately,":[41],"a":[42,76,109,141,212,229,253],"large":[43],"portion":[44],"process":[49],"many":[51],"applications":[52],"still":[54],"unknown":[55],"to":[56,63,118,139,160,167,185,203,216,236,245,262,266,282],"human":[57],"beings":[58],"so":[59],"it":[60],"have":[64,259,316],"expressive":[65,82],"learning":[68,92,134],"underlying":[70,94],"automatically.":[72],"Recently,":[73],"there":[74,122],"surge":[77],"research":[79],"body":[80],"Graph":[86,157],"Neural":[87],"Networks":[88],"(GNNs)":[89],"automatically":[91],"diffusion.":[96],"However,":[97],"instead":[101],"inverse":[103,111,177],"diffusion,":[106,209],"which":[107],"typical":[110],"problem":[112],"graphs":[114],"that":[115,234,306],"well-known":[117],"be":[119,124],"ill-posed":[120],"because":[121],"can":[123],"multiple":[125],"solutions":[126],"hence":[128],"different":[129],"from":[130],"traditional":[132],"(semi-)supervised":[133],"settings.":[135],"This":[136],"paper":[137],"aims":[138],"establish":[140],"generic":[142],"framework":[143],"invertible":[145,222],"graphs,":[153],"namely":[154],"Invertible":[155],"Validity-aware":[156],"Diffusion":[158],"(IVGD),":[159],"handle":[161],"major":[162],"challenges":[163],"including":[164],"1)":[165],"Difficulty":[166,184],"leverage":[168],"knowledge":[169],"modeling":[175],"their":[176],"processes":[178],"end-to-end":[181],"fashion,":[182],"2)":[183],"ensure":[186,246],"validity":[188,248],"inferred":[191,242,251,264],"sources,":[192,252],"3)":[194],"Efficiency":[195],"scalability":[197],"inference.":[200],"Specifically,":[201],"first,":[202],"inversely":[204],"infer":[205],"sources":[206,265],"we":[210,227],"propose":[211],"residual":[214],"scenario":[215],"make":[217],"existing":[218],"with":[223,273],"theoretical":[224],"guarantees;":[225],"second,":[226],"develop":[228],"novel":[230],"error":[231],"compensation":[232],"mechanism":[233],"learns":[235],"offset":[237],"errors":[239],"sources.":[243],"Finally,":[244],"new":[254],"set":[255],"validity-aware":[257],"layers":[258],"been":[260],"devised":[261],"project":[263],"feasible":[267],"regions":[268],"by":[269],"flexibly":[270],"encoding":[271],"constraints":[272],"unrolled":[274],"optimization":[275],"techniques.":[276],"A":[277],"linearization":[278],"technique":[279],"proposed":[281,288,294,308],"strengthen":[283],"efficiency":[285],"our":[287,307,318],"layers.":[289],"The":[290],"convergence":[291],"IVGD":[295,309],"proven":[297],"theoretically.":[298],"Extensive":[299],"experiments":[300],"nine":[302],"real-world":[303],"datasets":[304],"demonstrate":[305],"outperforms":[310],"state-of-the-art":[311],"comparison":[312],"methods":[313],"significantly.":[314],"We":[315],"released":[317],"code":[319],"at":[320],"https://github.com/xianggebenben/IVGD.":[321]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}