{"id":"https://openalex.org/W7164418408","doi":"https://doi.org/10.48550/arxiv.2606.11831","title":"From Uniform to Learned Graph Priors: Diffusion for Structure Discovery","display_name":"From Uniform to Learned Graph Priors: Diffusion for Structure Discovery","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164418408","doi":"https://doi.org/10.48550/arxiv.2606.11831"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11831","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11831","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.2606.11831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138479641","display_name":"Qi Shao (2394193)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138401064","display_name":"Hao Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138450158","display_name":"Jiawen Chen (589546)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiawen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138434696","display_name":"Duxin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Duxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138405007","display_name":"Wenwu Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Wenwu","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":0.8449000120162964,"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":0.8449000120162964,"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":0.04659999907016754,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.023399999365210533,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/inference","display_name":"Inference","score":0.7325999736785889},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5309000015258789},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4684000015258789},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43630000948905945},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.43220001459121704},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.36390000581741333},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.3504999876022339},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.3303000032901764}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7325999736785889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5633000135421753},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4415000081062317},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.36390000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3504999876022339},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C2781137444","wikidata":"https://www.wikidata.org/wiki/Q237105","display_name":"Sharpening","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27559998631477356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11831","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11831","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.2606.11831","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11831","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":{"Neural":[0],"relational":[1],"inference":[2,184],"(NRI)":[3],"methods":[4,19],"discover":[5],"interaction":[6],"graphs":[7],"from":[8],"trajectories":[9],"through":[10],"variational":[11],"reasoning":[12],"on":[13,22,123,152,167,199],"discrete":[14],"potential":[15],"edges.":[16],"However,":[17],"these":[18],"typically":[20,29],"rely":[21],"oversimplified,":[23],"factorized":[24],"graph":[25,74],"priors.":[26],"Such":[27],"priors,":[28],"nearing":[30],"uniform":[31],"distributions,":[32],"treat":[33],"edges":[34],"as":[35,88,147],"independent":[36],"entities.":[37],"This":[38],"systemic":[39],"misalignment":[40],"does":[41],"not":[42],"match":[43],"the":[44,55,110,124,136,153,174,180],"real-world":[45],"systems":[46],"and":[47,50,145,173,185],"yields":[48],"diffuse":[49],"indecisive":[51],"edge":[52,97,125,155,189],"posteriors":[53,98,126,190],"limiting":[54],"reliability":[56],"of":[57,182],"structural":[58,143],"discovery.":[59],"To":[60],"address":[61],"this,":[62],"we":[63],"propose":[64],"\\textit{Diff-prior},":[65],"a":[66,89,100,132,148,159],"diffusion-parameterized":[67],"adaptive":[68,116],"prior":[69,86,118],"used":[70],"to":[71,84,135],"calibrate":[72],"latent":[73],"distribution":[75,133],"rather":[76],"than":[77],"generate":[78],"graphs.":[79],"Our":[80],"core":[81],"insight":[82],"is":[83,197],"reframe":[85],"integration":[87],"learnable":[90],"denoising-style":[91],"calibration":[92,122],"that":[93,119,177],"organizes":[94],"scattered,":[95],"uncertain":[96],"into":[99],"more":[101,187],"reliable":[102],"overall":[103],"structure":[104,117,183],"which":[105,157],"can":[106],"be":[107],"trained":[108],"by":[109],"diffusion":[111],"model.":[112],"Diff-prior":[113,178],"learns":[114],"an":[115],"performs":[120],"structured":[121,164],"during":[127],"inference,":[128],"guiding":[129],"it":[130],"towards":[131],"closer":[134],"underlying":[137],"structure.":[138],"The":[139,195],"diff-prior":[140],"operates":[141],"before":[142],"sampling":[144],"acts":[146],"denoising":[149],"calibrator":[150],"directly":[151],"encoder":[154],"distribution,":[156],"provides":[158],"generic":[160],"training":[161],"paradigm":[162],"over":[163],"variables.":[165],"Experiments":[166],"standard":[168],"benchmarks":[169],"validated":[170],"our":[171],"framework,":[172],"results":[175],"indicate":[176],"improves":[179],"performance":[181],"generates":[186],"decisive":[188],"across":[191],"multiple":[192],"NRI-family":[193],"architectures.":[194],"code":[196],"available":[198],"https://github.com/Hardy158118/Diffprior.":[200]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}