{"id":"https://openalex.org/W7165638236","doi":"https://doi.org/10.48550/arxiv.2606.22914","title":"PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs","display_name":"PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165638236","doi":"https://doi.org/10.48550/arxiv.2606.22914"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22914","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031387025","display_name":"Guoguo Ai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ai, Guoguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075093679","display_name":"Chaoxi Niu","orcid":"https://orcid.org/0000-0003-4529-8560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Chaoxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139188397","display_name":"Hui Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139164732","display_name":"Joey Tianyi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Joey Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139147073","display_name":"Yew-Soon Ong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ong, Yew-Soon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039104219","display_name":"Guansong Pang","orcid":"https://orcid.org/0000-0002-9877-2716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Guansong","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.42820000648498535,"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":0.42820000648498535,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.23600000143051147,"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":0.04349999874830246,"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/snapshot","display_name":"Snapshot (computer storage)","score":0.5849000215530396},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48559999465942383},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.40230000019073486},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.321399986743927},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.3206000030040741},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.2953000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549999952316284},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.5849000215530396},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4505000114440918},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22914","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22914","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Activities":[0],"in":[1,11,28,34,82],"numerous":[2],"evolving":[3,72,141],"systems":[4],"can":[5,122,151],"be":[6,123],"represented":[7],"as":[8],"dynamic":[9,20,119,165],"graphs":[10,21],"snapshot":[12],"form":[13],"at":[14],"different":[15],"time":[16],"intervals,":[17],"i.e.,":[18],"discrete-time":[19],"(DTDGs).":[22],"Existing":[23],"methods":[24],"show":[25,144,181],"impressive":[26],"advances":[27],"capturing":[29],"historical":[30,50],"temporal":[31],"evolution":[32],"patterns":[33],"DTDGs,":[35],"but":[36],"they":[37],"focus":[38],"on":[39,125,176],"addressing":[40],"an":[41,117],"offline":[42],"learning":[43,106],"setting,":[44],"where":[45],"models":[46],"are":[47],"trained":[48],"using":[49],"snapshots":[51,60,76],"once":[52],"and":[53,77,137,159,183],"then":[54],"evaluated":[55],"to":[56,66,135],"all":[57],"subsequent":[58],"graph":[59,75,85,120],"without":[61],"further":[62,169],"updating.":[63],"This":[64],"fails":[65],"capture":[67],"1)":[68],"the":[69,79,83,140],"nature":[70],"of":[71,131,186],"complexities":[73],"across":[74],"2)":[78],"distribution":[80],"shift":[81],"testing":[84],"snapshots.":[86],"To":[87],"address":[88],"these":[89],"problems,":[90],"we":[91],"propose":[92],"PromptDyG,":[93],"a":[94,108,126,153],"novel":[95],"framework":[96],"that":[97,116,146,180],"leverages":[98],"unsupervised":[99,148],"test-time":[100],"Prompt":[101],"adaptation":[102,150],"for":[103],"Dynamic":[104],"Graph":[105],"under":[107],"live-update":[109],"online":[110],"setting.":[111],"The":[112],"key":[113],"insight":[114],"is":[115,168],"expressive":[118],"prompt":[121,149],"learned":[124],"frozen":[127],"backbone":[128],"via":[129],"minimization":[130],"feature-wise,":[132],"label-free":[133],"entropy":[134],"efficiently":[136],"continuously":[138],"model":[139],"patterns.":[142],"We":[143],"theoretically":[145],"this":[147],"guarantee":[152],"larger":[154],"similarity":[155],"margin":[156],"between":[157],"positive":[158],"negative":[160],"pairs,":[161],"facilitating":[162],"more":[163],"accurate":[164],"predictions.":[166],"It":[167],"confirmed":[170],"by":[171],"our":[172],"extensive":[173],"empirical":[174],"results":[175],"six":[177],"benchmark":[178],"datasets":[179],"consistent":[182],"significant":[184],"improvements":[185],"PromptDyG":[187],"over":[188],"state-of-the-art":[189],"baselines.":[190]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}