{"id":"https://openalex.org/W7204686885","doi":"https://doi.org/10.21203/rs.3.rs-10869094/v1","title":"Learning Calibrated and Transferable Node-Level Infection Risk in Stochastic Epidemics on Complex Networks","display_name":"Learning Calibrated and Transferable Node-Level Infection Risk in Stochastic Epidemics on Complex Networks","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7204686885","doi":"https://doi.org/10.21203/rs.3.rs-10869094/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-10869094/v1","doi":"https://doi.org/10.21203/rs.3.rs-10869094/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10869094/v1","pdf_url":"https://www.researchsquare.com/article/rs-10869094/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-10869094/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037399554","display_name":"Pietro Hiram Guzzi","orcid":"https://orcid.org/0000-0001-5542-2997","observed_orcids":["https://orcid.org/0000-0001-5542-2997"]},"institutions":[{"id":"https://openalex.org/I36443711","display_name":"Magna Graecia University","ror":"https://ror.org/0530bdk91","country_code":"IT","type":"education","lineage":["https://openalex.org/I36443711"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Hiram Guzzi","raw_affiliation_strings":["Magna Graecia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Magna Graecia University","institution_ids":["https://openalex.org/I36443711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109702910","display_name":"Annamaria Defilippo","orcid":"https://orcid.org/0009-0004-0421-7650","observed_orcids":["https://orcid.org/0009-0004-0421-7650"]},"institutions":[{"id":"https://openalex.org/I36443711","display_name":"Magna Graecia University","ror":"https://ror.org/0530bdk91","country_code":"IT","type":"education","lineage":["https://openalex.org/I36443711"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Annamaria Defilippo","raw_affiliation_strings":["Magna Graecia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Magna Graecia University","institution_ids":["https://openalex.org/I36443711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059223728","display_name":"Ugo Lomoio","orcid":"https://orcid.org/0000-0001-8150-0039","observed_orcids":["https://orcid.org/0000-0001-8150-0039"]},"institutions":[{"id":"https://openalex.org/I36443711","display_name":"Magna Graecia University","ror":"https://ror.org/0530bdk91","country_code":"IT","type":"education","lineage":["https://openalex.org/I36443711"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ugo Lomoio","raw_affiliation_strings":["Magna Graecia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Magna Graecia University","institution_ids":["https://openalex.org/I36443711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148853751","display_name":"Francesco Vissicchio","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36443711","display_name":"Magna Graecia University","ror":"https://ror.org/0530bdk91","country_code":"IT","type":"education","lineage":["https://openalex.org/I36443711"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Vissicchio","raw_affiliation_strings":["Magna Graecia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Magna Graecia University","institution_ids":["https://openalex.org/I36443711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121133111","display_name":"Pierangelo Veltri","orcid":"https://orcid.org/0000-0003-2494-0294","observed_orcids":["https://orcid.org/0000-0003-2494-0294"]},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pierangelo Veltri","raw_affiliation_strings":["University of Calabria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Calabria","institution_ids":["https://openalex.org/I45204951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9868000149726868,"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"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9868000149726868,"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/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.010499999858438969,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10410","display_name":"COVID-19 epidemiological studies","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2611","display_name":"Modeling and Simulation"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/infection-risk-prediction","display_name":"infection risk prediction","score":0.8009999990463257},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7919999957084656},{"id":"https://openalex.org/keywords/out-of-distribution-evaluation","display_name":"out-of-distribution evaluation","score":0.9169999957084656},{"id":"https://openalex.org/keywords/contact-networks","display_name":"contact networks","score":0.5270000100135803},{"id":"https://openalex.org/keywords/model-calibration","display_name":"model calibration","score":0.44200000166893005},{"id":"https://openalex.org/keywords/integrated-gradients","display_name":"integrated gradients","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C34947359","wikidata":"https://www.wikidata.org/wiki/Q665189","display_name":"Complex network","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.522599995136261},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C2776272983","wikidata":"https://www.wikidata.org/wiki/Q7336291","display_name":"Risk of infection","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C3019879152","wikidata":"https://www.wikidata.org/wiki/Q2712836","display_name":"Infection risk","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.26649999618530273}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21203/rs.3.rs-10869094/v1","doi":"https://doi.org/10.21203/rs.3.rs-10869094/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10869094/v1","pdf_url":"https://www.researchsquare.com/article/rs-10869094/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},{"id":"doi:10.5281/zenodo.22172781","doi":"https://doi.org/10.5281/zenodo.22172781","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22172781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-10869094/v1","doi":"https://doi.org/10.21203/rs.3.rs-10869094/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10869094/v1","pdf_url":"https://www.researchsquare.com/article/rs-10869094/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5683000087738037}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204686885.pdf","grobid_xml":"https://content.openalex.org/works/W7204686885.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3115704193","https://openalex.org/W1511258125","https://openalex.org/W7223100882","https://openalex.org/W7165140123","https://openalex.org/W4402782017","https://openalex.org/W3211880369","https://openalex.org/W3161588905","https://openalex.org/W2953252218","https://openalex.org/W2604291108","https://openalex.org/W3140253027"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],":":[2,49,134,262],"Predicting":[3],"future":[4],"infection":[5],"risk":[6,127,169,225,244,265],"on":[7,55,88,196],"contact":[8],"networks":[9,193],"requires":[10],"jointly":[11],"accounting":[12],"for":[13,122,130,180,298],"epidemic":[14,67,303],"state,":[15,68],"network":[16,46,84],"structure,":[17],"and":[18,42,59,91,97,112,117,125,158,173,191,255,275],"stochastic":[19,60],"uncertainty.":[20],"We":[21],"investigate":[22],"whether":[23],"the":[24,143,214,249,296],"probability":[25],"that":[26,285],"a":[27,38,146,258,270],"currently":[28],"susceptible":[29,137,234,239],"node":[30],"will":[31],"become":[32],"infected":[33],"can":[34,266,288],"be":[35,267],"learned":[36,268],"as":[37,269],"calibrated":[39,271],"graph":[40,82,141,273,304],"function":[41,274],"transferred":[43],"to":[44,74,187,213,220,233,242],"unseen":[45,140,188,197],"structures.":[47],"Methods":[48],"Stochastic":[50,263],"SIR":[51],"epidemics":[52],"were":[53,72,120],"simulated":[54],"Erd\\H{o}s--R\\'enyi,":[56],"Barab\\'asi--Albert,":[57],"Watts--Strogatz,":[58],"block-model":[61],"networks.":[62],"For":[63],"each":[64],"partially":[65],"observed":[66],"repeated":[69],"Monte-Carlo":[70,259],"continuations":[71],"used":[73,121],"estimate":[75],"soft":[76],"node-level":[77,272],"future-infection":[78,264],"probabilities.":[79],"A":[80],"parameter-conditioned":[81],"neural":[83],"(GNN)":[85],"was":[86,103,128],"trained":[87],"these":[89],"probabilities":[90],"evaluated":[92,129],"using":[93],"strict":[94],"graph-disjoint":[95],"splits":[96],"leave-one-topology-out":[98],"structural":[99,286],"out-of-distribution":[100,300],"tests.":[101],"Performance":[102],"compared":[104],"with":[105],"ridge":[106,172],"regression,":[107],"gradient":[108],"boosting,":[109],"centrality-,":[110],"exposure-,":[111],"diffusion-based":[113],"baselines.":[114],"Integrated":[115,206],"Gradients":[116,207],"edge":[118],"occlusion":[119],"mechanistic":[123],"auditing,":[124],"predicted":[126,224],"targeted":[131],"intervention.":[132],"Results":[133],"On":[135],"13,097":[136],"nodes":[138,240],"from":[139],"realizations,":[142],"GNN":[144,243],"achieved":[145],"Brier":[147],"score":[148],"of":[149,152,156,162,210,238,252,293],"$7.29\\times10^{-4}$,":[150],"MAE":[151],"0.0173,":[153],"Spearman":[154],"correlation":[155],"0.978,":[157],"expected":[159],"calibration":[160],"error":[161],"0.003.":[163],"It":[164],"provided":[165],"more":[166,229],"accurate":[167],"absolute":[168],"estimates":[170],"than":[171,230],"gradient-boosted":[174],"models,":[175],"although":[176],"boosting":[177],"remained":[178,185],"competitive":[179],"within-episode":[181],"ranking.":[182],"Structural":[183],"transfer":[184],"strong":[186],"ER,":[189],"WS,":[190],"SBM":[192],"but":[194],"degraded":[195],"BA":[198],"graphs,":[199],"which":[200],"exhibited":[201],"substantially":[202],"greater":[203],"degree":[204],"heterogeneity.":[205],"assigned":[208],"76.8\\%":[209],"state-related":[211],"attribution":[212],"infectious":[215,221],"compartment,":[216],"while":[217],"removing":[218,231],"edges":[219,232],"neighbors":[222],"changed":[223],"approximately":[226,246],"6.7":[227],"times":[228,248],"neighbors.":[235],"Targeting":[236],"5\\%":[237],"according":[241],"produced":[245],"three":[247],"attack-rate":[250],"reduction":[251],"random":[253],"targeting":[254],"closely":[256],"matched":[257],"oracle.":[260],"Conclusions":[261],"translated":[276],"into":[277],"effective":[278],"intervention":[279],"decisions.":[280],"However,":[281],"topology-level":[282],"experiments":[283],"show":[284],"heterogeneity":[287],"define":[289],"an":[290],"important":[291],"boundary":[292],"transferability,":[294],"emphasizing":[295],"need":[297],"explicit":[299],"evaluation":[301],"in":[302],"learning.":[305]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-08-31T00:00:00"}