{"id":"https://openalex.org/W7147483461","doi":"https://doi.org/10.48550/arxiv.2603.29384","title":"Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs","display_name":"Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147483461","doi":"https://doi.org/10.48550/arxiv.2603.29384"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29384","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29384","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29384","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132679720","display_name":"Yuxuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Yuxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132577588","display_name":"Wenchao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wenchao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132588801","display_name":"Haozhao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haozhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132590143","display_name":"Zhiming He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Zhiming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641489","display_name":"Zhaofeng Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Zhaofeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089292160","display_name":"Chongyang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chongyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000977496","display_name":"Peichao Wang","orcid":"https://orcid.org/0000-0003-4811-5272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Peichao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132546202","display_name":"Boyuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Boyuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5132679720"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.5548999905586243,"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":0.5548999905586243,"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":0.25929999351501465,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.04320000112056732,"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/spurious-relationship","display_name":"Spurious relationship","score":0.7949000000953674},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5054000020027161},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4528999924659729},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.43529999256134033},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42480000853538513},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.374099999666214},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3596999943256378},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3422999978065491}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7949000000953674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433000206947327},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5353000164031982},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42480000853538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38960000872612},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3125},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29384","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29384","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.29384","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29384","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.439970463514328,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0,91],"Graph":[1,191],"Learning":[2,92],"(FGL)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,75,104,125,160],"powerful":[8],"paradigm":[9],"for":[10,28],"decentralized":[11],"training":[12],"of":[13,60,78,140],"graph":[14],"neural":[15],"networks":[16],"while":[17],"preserving":[18],"data":[19],"privacy.":[20],"However,":[21],"existing":[22],"FGL":[23],"methods":[24],"are":[25,45],"predominantly":[26],"designed":[27],"static":[29],"graphs":[30],"and":[31,54,57,84,148,167,177],"rely":[32],"on":[33,186],"parameter":[34],"averaging":[35],"or":[36],"distribution":[37],"alignment,":[38],"which":[39,110],"implicitly":[40],"assume":[41],"that":[42,71,129,163,195],"all":[43],"features":[44],"equally":[46],"transferable":[47,113],"across":[48,181],"clients,":[49],"overlooking":[50],"both":[51],"the":[52,58,138],"spatial":[53],"temporal":[55],"heterogeneity":[56,189],"presence":[59],"client-specific":[61,82,117],"knowledge":[62,115,179],"in":[63,90],"real-world":[64],"graphs.":[65],"In":[66,156],"this":[67,100],"work,":[68],"we":[69,102,123,158],"identify":[70],"such":[72],"assumptions":[73],"create":[74],"vicious":[76],"cycle":[77],"spurious":[79,146],"representation":[80,150],"entanglement,":[81],"interference,":[83],"negative":[85],"transfer,":[86],"degrading":[87],"generalization":[88],"performance":[89],"over":[93],"Dynamic":[94],"Spatio-Temporal":[95,190],"Graphs":[96],"(FSTG).":[97],"To":[98],"address":[99],"issue,":[101],"propose":[103,159],"novel":[105],"causality-inspired":[106],"framework":[107],"named":[108],"SC-FSGL,":[109],"explicitly":[111],"decouples":[112],"causal":[114,143,165],"from":[116,145],"noise":[118],"through":[119,133],"representation-level":[120],"interventions.":[121],"Specifically,":[122],"introduce":[124],"Conditional":[126],"Separation":[127],"Module":[128],"simulates":[130],"soft":[131],"interventions":[132],"client":[134,154],"conditioned":[135],"masks,":[136],"enabling":[137],"disentanglement":[139],"invariant":[141],"spatio-temporal":[142,183],"factors":[144],"signals":[147],"mitigating":[149],"entanglement":[151],"caused":[152],"by":[153],"heterogeneity.":[155],"addition,":[157],"Causal":[161],"Codebook":[162],"clusters":[164],"prototypes":[166],"aligns":[168],"local":[169],"representations":[170],"via":[171],"contrastive":[172],"learning,":[173],"promoting":[174],"cross-client":[175],"consistency":[176],"facilitating":[178],"sharing":[180],"diverse":[182,188],"patterns.":[184],"Experiments":[185],"five":[187],"(STG)":[192],"datasets":[193],"show":[194],"SC-FSGL":[196],"outperforms":[197],"state-of-the-art":[198],"methods.":[199]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}