{"id":"https://openalex.org/W7162021003","doi":"https://doi.org/10.48550/arxiv.2605.20188","title":"GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation","display_name":"GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7162021003","doi":"https://doi.org/10.48550/arxiv.2605.20188"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20188","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.20188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047752515","display_name":"K. B. Saxena","orcid":"https://orcid.org/0000-0001-7049-9685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saxena, Krati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067304768","display_name":"Tomohiro Shibata","orcid":"https://orcid.org/0000-0002-8766-4250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shibata, Tomohiro","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/T13702","display_name":"Machine Learning in Healthcare","score":0.9819999933242798,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9819999933242798,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0026000000070780516,"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":0.0024999999441206455,"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":0.6866999864578247},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.451200008392334},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43619999289512634},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.41679999232292175},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.40779998898506165},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.38519999384880066}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6866999864578247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611299991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5138000249862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48339998722076416},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43619999289512634},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.40779998898506165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C45827449","wikidata":"https://www.wikidata.org/wiki/Q5270338","display_name":"Diagnosis code","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C56173144","wikidata":"https://www.wikidata.org/wiki/Q1539893","display_name":"Pharmacophore","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C3020672099","wikidata":"https://www.wikidata.org/wiki/Q857354","display_name":"Longitudinal data","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20188","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20188","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recommending":[0],"safe":[1],"and":[2,27,77,86,100,111,153],"effective":[3],"medication":[4,61,156],"combinations":[5],"from":[6],"electronic":[7],"health":[8],"records":[9],"(EHRs)":[10],"is":[11,72],"a":[12,59,118],"core":[13],"clinical":[14],"AI":[15],"problem,":[16],"yet":[17],"it":[18],"remains":[19],"difficult":[20],"because":[21],"patient":[22],"trajectories":[23],"are":[24,93],"long,":[25],"noisy,":[26],"clinically":[28,154],"heterogeneous.":[29],"Existing":[30],"methods":[31],"typically":[32],"excel":[33],"at":[34,74,162],"either":[35],"temporal":[36],"modeling":[37],"across":[38,87],"visits":[39],"or":[40],"pharmacological":[41,91,148],"knowledge":[42],"integration":[43],"(e.g.,":[44],"drug-drug":[45],"interactions,":[46],"DDIs),":[47],"but":[48],"rarely":[49],"achieve":[50],"both":[51,75],"while":[52,90,116],"robustly":[53],"suppressing":[54],"noise.":[55],"We":[56,124,158],"present":[57],"GraphDiffMed,":[58],"knowledge-constrained":[60],"recommendation":[62,109],"framework":[63],"built":[64],"on":[65,98],"dual-scale":[66],"Differential":[67,70],"Attention":[68],"v2.":[69],"attention":[71,146],"applied":[73],"intra-visit":[76],"inter-visit":[78],"levels":[79],"to":[80],"filter":[81],"spurious":[82],"signals":[83],"within":[84],"encounters":[85],"longitudinal":[88],"history,":[89],"constraints":[92,149],"incorporated":[94],"during":[95],"learning.":[96],"Experiments":[97],"MIMIC-III":[99],"ablation":[101],"studies":[102],"show":[103],"that":[104,127,143],"this":[105],"design":[106],"consistently":[107],"improves":[108],"quality":[110],"ranking":[112],"over":[113],"strong":[114],"baselines":[115],"achieving":[117],"more":[119,151],"favorable":[120],"safety":[121],"performance":[122],"balance.":[123],"further":[125],"find":[126],"the":[128],"strongest-performing":[129],"configuration":[130],"uses":[131],"only":[132],"demographic":[133],"auxiliary":[134],"features":[135],"under":[136],"our":[137,160],"experimental":[138],"setting.":[139],"Overall,":[140],"GraphDiffMed":[141],"demonstrates":[142],"combining":[144],"noise-aware":[145],"with":[147],"yields":[150],"reliable":[152],"meaningful":[155],"recommendation.":[157],"open-source":[159],"code":[161],"https://github.com/saxenakrati09/GraphDiffMed.":[163]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-22T00:00:00"}