{"id":"https://openalex.org/W4415536375","doi":"https://doi.org/10.1145/3746027.3755820","title":"Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation","display_name":"Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536375","doi":"https://doi.org/10.1145/3746027.3755820"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755820","doi":"https://doi.org/10.1145/3746027.3755820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755820","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5102373522","display_name":"Xinshu Li","orcid":"https://orcid.org/0000-0002-1202-3993","observed_orcids":["https://orcid.org/0000-0002-1202-3993"]},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xinshu Li","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1202-3993","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069688625","display_name":"Ruibao Wang","orcid":"https://orcid.org/0009-0000-6617-0369","observed_orcids":["https://orcid.org/0009-0000-6617-0369"]},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ruoyu Wang","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0000-6617-0369","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030365210","display_name":"Erdun Gao","orcid":"https://orcid.org/0000-0003-1736-2764","observed_orcids":["https://orcid.org/0000-0003-1736-2764"]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Erdun Gao","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1736-2764","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102023771","display_name":"Mingming Gong","orcid":"https://orcid.org/0000-0001-7147-5589","observed_orcids":["https://orcid.org/0000-0001-7147-5589","https://orcid.org/0009-0002-3454-915X"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","AU"],"is_corresponding":false,"raw_author_name":"Mingming Gong","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia and Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-7147-5589","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia and Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X","observed_orcids":["https://orcid.org/0000-0002-4149-839X","https://orcid.org/0009-0001-9562-1904","https://orcid.org/0000-0003-2772-0385"]},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["CSIRO's Data61, Sydney, Australia and University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"CSIRO's Data61, Sydney, Australia and University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I31746571","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.472,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86788683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5208","last_page":"5217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9639000296592712,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9639000296592712,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.006500000134110451,"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":0.002899999963119626,"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/prompt-learning","display_name":"prompt learning","score":0.9520000219345093},{"id":"https://openalex.org/keywords/counterfactual-generation","display_name":"counterfactual generation","score":0.796999990940094},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.9089999794960022},{"id":"https://openalex.org/keywords/causal-inference","display_name":"causal inference","score":0.625},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9259999990463257},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5640000104904175},{"id":"https://openalex.org/keywords/image-text-retrieval","display_name":"image-text retrieval","score":0.9909999966621399},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.968999981880188},{"id":"https://openalex.org/keywords/unseen-category-generalization","display_name":"unseen category generalization","score":0.7760000228881836}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9039000272750854},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.7709000110626221},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.7311999797821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916000008583069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.507099986076355},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C32254414","wikidata":"https://www.wikidata.org/wiki/Q4724364","display_name":"Algorithmic learning theory","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755820","doi":"https://doi.org/10.1145/3746027.3755820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755820","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1977295328","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2146531590","https://openalex.org/W2533598788","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2981852735","https://openalex.org/W3091940082","https://openalex.org/W3098267758","https://openalex.org/W3112027221","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3214023923","https://openalex.org/W4288099666","https://openalex.org/W4307935822","https://openalex.org/W4310381212","https://openalex.org/W4312310776","https://openalex.org/W4317940242","https://openalex.org/W4320723628","https://openalex.org/W4368754753","https://openalex.org/W4385572827","https://openalex.org/W4386071547","https://openalex.org/W4386075552","https://openalex.org/W4393147317","https://openalex.org/W4406560402","https://openalex.org/W4409362346"],"related_works":["https://openalex.org/W7162337482","https://openalex.org/W6910459569","https://openalex.org/W4403487431","https://openalex.org/W4404313812","https://openalex.org/W7212222294","https://openalex.org/W4401157522","https://openalex.org/W4414271666","https://openalex.org/W7167301775","https://openalex.org/W3212340273","https://openalex.org/W4417457274"],"abstract_inverted_index":{"Prompt":[0],"learning":[1,56,113],"has":[2],"garnered":[3],"attention":[4],"for":[5],"its":[6],"efficiency":[7],"over":[8],"traditional":[9],"model":[10],"training":[11],"and":[12,70,155],"fine-tuning.":[13],"However,":[14],"existing":[15],"methods,":[16],"constrained":[17],"by":[18],"inadequate":[19],"theoretical":[20,91],"foundations,":[21],"encounter":[22],"difficulties":[23],"in":[24,89,163],"achieving":[25],"causally":[26],"invariant":[27],"prompts,":[28],"ultimately":[29],"falling":[30],"short":[31],"of":[32,73,80,98,125,135],"capturing":[33],"robust":[34],"features":[35,134],"that":[36,82,115,127,142],"generalize":[37],"effectively":[38],"across":[39,147],"categories.":[40,165],"To":[41],"address":[42],"these":[43],"challenges,":[44],"we":[45],"introduce":[46],"the":[47,68,74,78,84,96,117,122,132,136],"DiCap":[48],"model,":[49,76],"a":[50,60,111],"theoretically":[51],"grounded":[52],"Diffusion-based":[53],"Counterfactual":[54],"prompt":[55],"framework,":[57],"which":[58],"leverages":[59,116],"diffusion":[61],"process":[62],"to":[63],"iteratively":[64],"sample":[65],"gradients":[66],"from":[67],"marginal":[69],"conditional":[71],"distributions":[72],"causal":[75,133],"guiding":[77],"generation":[79],"counterfactuals":[81],"satisfy":[83],"minimal":[85],"sufficiency":[86],"criterion.":[87],"Grounded":[88],"rigorous":[90],"derivations,":[92],"this":[93],"approach":[94],"guarantees":[95],"identifiability":[97],"counterfactual":[99],"outcomes":[100],"while":[101],"imposing":[102],"strict":[103],"bounds":[104],"on":[105],"estimation":[106],"errors.":[107],"We":[108],"further":[109],"employ":[110],"contrastive":[112],"framework":[114],"generated":[118],"counterfactuals,":[119],"thereby":[120],"enabling":[121],"refined":[123],"extraction":[124],"prompts":[126],"are":[128],"precisely":[129],"aligned":[130],"with":[131,159],"data.":[137],"Extensive":[138],"experimental":[139],"results":[140],"demonstrate":[141],"our":[143],"method":[144],"performs":[145],"excellently":[146],"tasks":[148],"such":[149],"as":[150],"image":[151],"classification,":[152],"image-text":[153],"retrieval,":[154],"visual":[156],"question":[157],"answering,":[158],"particularly":[160],"strong":[161],"advantages":[162],"unseen":[164]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-25T00:00:00"}