{"id":"https://openalex.org/W7172022335","doi":"https://doi.org/10.48550/arxiv.2607.27289","title":"TIER-MoE: Trust-Informed Expert Routing via Conditional Modality Risk for Multimodal Fusion in Biomedical Classification","display_name":"TIER-MoE: Trust-Informed Expert Routing via Conditional Modality Risk for Multimodal Fusion in Biomedical Classification","publication_year":2026,"publication_date":"2026-07-29","ids":{"openalex":"https://openalex.org/W7172022335","doi":"https://doi.org/10.48550/arxiv.2607.27289"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.27289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27289","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.2607.27289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112627578","display_name":"Yu Chang","orcid":"https://orcid.org/0000-0001-9954-921X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144172404","display_name":"Anzhe Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Anzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144163928","display_name":"Chenwei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Chenwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144151653","display_name":"Zhuoran Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhuoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144130600","display_name":"Jiahao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiahao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074576951","display_name":"Tamoghna Chattopadhyay","orcid":"https://orcid.org/0000-0002-3146-6845"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chattopadhyay, Tamoghna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144147315","display_name":"Sophia I. Thomopoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomopoulos, Sophia I.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144105764","display_name":"Paul M. Thompson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thompson, Paul M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144174355","display_name":"Liyue Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Liyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5144096093","display_name":"Paul Bogdan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogdan, Paul","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.21899999678134918,"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":0.21899999678134918,"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":0.15760000050067902,"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/T11438","display_name":"Retinal Imaging and Analysis","score":0.07490000128746033,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5889000296592712},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5120999813079834},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5013999938964844},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4169999957084656},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.3991999924182892},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3280999958515167},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3199999928474426},{"id":"https://openalex.org/keywords/brier-score","display_name":"Brier score","score":0.3093999922275543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6280999779701233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6115000247955322},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5120999813079834},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C153668964","wikidata":"https://www.wikidata.org/wiki/Q27636","display_name":"Majority rule","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.27289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27289","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.2607.27289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27289","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":{"The":[0],"promise":[1],"of":[2,10],"multimodal":[3,23,125,133],"fusion":[4,27,43],"lies":[5],"in":[6,152,161],"combining":[7],"complementary":[8],"sources":[9],"evidence,":[11],"yet":[12],"more":[13],"evidence":[14],"does":[15,44],"not":[16,45,100],"always":[17],"yield":[18],"a":[19,40,57,67],"better":[20],"prediction.":[21],"Recent":[22],"models":[24,97],"have":[25],"advanced":[26],"through":[28],"richer":[29],"cross-modal":[30],"interaction":[31],"and":[32,142,155,163,166],"sample-adaptive":[33],"fusion.":[34],"However,":[35],"the":[36,78,103,108],"influence":[37],"assigned":[38],"to":[39,56,86,170],"modality":[41,75],"during":[42],"reveal":[46],"whether":[47],"that":[48,72,98],"source":[49],"is":[50,84,90],"unreliable,":[51],"redundant,":[52],"or":[53],"poorly":[54],"matched":[55],"specialized":[58],"expert.":[59],"To":[60],"address":[61],"this":[62],"limitation,":[63],"we":[64],"introduce":[65],"TIER-MoE,":[66],"risk-guided":[68],"subspace":[69,113],"mixture-of-experts":[70],"model":[71],"defines":[73],"sample-specific":[74],"reliability":[76],"as":[77],"prediction":[79],"loss":[80],"its":[81,147],"unimodal":[82],"predictor":[83],"expected":[85],"incur.":[87],"This":[88],"risk":[89,110],"learned":[91],"from":[92],"out-of-fold":[93],"predictions":[94],"generated":[95],"by":[96],"were":[99],"trained":[101],"on":[102,130],"corresponding":[104],"sample.":[105],"TIER-MoE":[106,129],"combines":[107],"estimated":[109],"with":[111,158],"expert-specific":[112],"compatibility":[114],"for":[115],"sparse":[116],"modality-expert":[117],"routing,":[118],"while":[119],"an":[120,171],"always-active":[121],"shared":[122],"path":[123],"preserves":[124],"complementarity.":[126],"We":[127],"evaluate":[128],"four":[131],"public":[132],"biomedical":[134],"datasets":[135],"spanning":[136],"Alzheimer's":[137],"disease":[138],"status,":[139],"skin-lesion":[140],"malignancy,":[141],"retinal":[143],"classification.":[144],"Results":[145],"demonstrate":[146],"superiority":[148],"over":[149],"state-of-the-art":[150],"methods":[151],"predictive":[153],"performance":[154],"probability":[156],"calibration,":[157],"consistent":[159],"improvements":[160],"Macro-F1":[162],"Brier":[164],"score":[165],"strong":[167],"zero-shot":[168],"generalization":[169],"external":[172],"cohort.":[173]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}