{"id":"https://openalex.org/W7134984285","doi":"https://doi.org/10.1109/icdmw69685.2025.00366","title":"Leveraging Hybrid Representations for Robust Molecular Property Prediction in Low-Data Regimes","display_name":"Leveraging Hybrid Representations for Robust Molecular Property Prediction in Low-Data Regimes","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134984285","doi":"https://doi.org/10.1109/icdmw69685.2025.00366"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"type":"article","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/A5008787905","display_name":"Alex X. Liu","orcid":"https://orcid.org/0000-0002-6916-1326"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alex Liu","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering,United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering,United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023045957","display_name":"Haomin Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haomin Zhuang","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering,United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering,United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029114040","display_name":"Olaf Wiest","orcid":"https://orcid.org/0000-0001-9316-7720"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olaf Wiest","raw_affiliation_strings":["University of Notre Dame,Department of Chemistry and Biochemistry,United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Chemistry and Biochemistry,United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010484591","display_name":"Ying Cheng","orcid":"https://orcid.org/0000-0002-0664-7206"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["University of Notre Dame,Department of Psychology,United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Psychology,United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125774395","display_name":"Xiangliang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangliang Zhang","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering,United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering,United States","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008787905"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58510706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2870","last_page":"2879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.3296000063419342,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.3296000063419342,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.15389999747276306,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.06870000064373016,"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/property","display_name":"Property (philosophy)","score":0.5809999704360962},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.34700000286102295},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3467000126838684},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2955000102519989},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.28139999508857727},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27799999713897705}],"concepts":[{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5388000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3467000126838684},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29420000314712524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W2159887157","https://openalex.org/W2295598076","https://openalex.org/W2461470610","https://openalex.org/W2578240541","https://openalex.org/W2594183968","https://openalex.org/W2791355014","https://openalex.org/W2947423323","https://openalex.org/W2966357564","https://openalex.org/W3038823641","https://openalex.org/W3165931875","https://openalex.org/W4393147868"],"related_works":[],"abstract_inverted_index":{"Molecular":[0],"machine":[1],"learning":[2],"faces":[3],"a":[4,56,61],"persistent":[5],"tradeoff":[6],"between":[7],"interpretability":[8,148],"and":[9,13,50,78,90,106,138,143,157,170,193],"predictive":[10,21],"accuracy.":[11],"Descriptors":[12],"fingerprints":[14,72,139],"provide":[15,140],"chemically":[16],"meaningful":[17],"features":[18],"but":[19],"limited":[20],"power,":[22],"while":[23],"learned":[24],"representations":[25,67],"from":[26],"graph":[27],"neural":[28],"networks":[29],"(GNNs)":[30],"or":[31],"SMILES-based":[32],"models":[33],"achieve":[34],"high":[35],"accuracy":[36],"at":[37],"the":[38,82,121,183],"expense":[39],"of":[40,64,130],"transparency.":[41],"In":[42],"this":[43,160],"study,":[44],"we":[45],"restrict":[46],"experiments":[47],"to":[48,99,111,118,190],"descriptors":[49,70,105,137],"fixed":[51],"fingerprints,":[52,119],"leaving":[53],"embeddings":[54],"as":[55],"future":[57],"extension.":[58],"We":[59],"conduct":[60],"systematic":[62],"evaluation":[63],"hybrid":[65,164],"molecular":[66,174],"that":[68,136,147,163],"combine":[69],"with":[71,120],"for":[73,173,187],"property":[74,175],"prediction":[75],"across":[76],"classification":[77],"regression":[79],"tasks.":[80],"On":[81],"BBBP":[83],"(blood-brain":[84],"barrier":[85],"permeability),":[86],"ESOL":[87],"(aqueous":[88],"solubility),":[89],"FreeSolv":[91],"(hydration":[92],"free":[93],"energy)":[94],"datasets,":[95],"hybrids":[96],"yield":[97],"up":[98,110],"7":[100],"%":[101],"higher":[102],"ROC-AUC":[103],"than":[104],"reduce":[107],"RMSE":[108],"by":[109],"<tex":[112,127],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[113,128],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{4":[114],"8":[115],"\\%}$</tex>":[116],"relative":[117],"largest":[122],"gains":[123],"in":[124],"low-data":[125],"regimes":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{(10-25\\%}$</tex>":[129],"training":[131],"data).":[132],"Ablation":[133],"studies":[134],"show":[135],"complementary":[141],"signals,":[142],"feature":[144,165],"analyses":[145],"confirm":[146],"is":[149,167,180],"preserved.":[150],"By":[151],"quantifying":[152],"robustness":[153],"under":[154],"both":[155],"full-data":[156],"data-scarce":[158],"settings,":[159],"study":[161],"demonstrates":[162],"fusion":[166],"an":[168],"effective":[169],"reliable":[171],"strategy":[172],"prediction.":[176],"The":[177],"complete":[178],"framework":[179],"integrated":[181],"into":[182],"Hands-On":[184],"Data":[185],"Science":[186],"Chemists":[188],"platform":[189],"support":[191],"reproducibility":[192],"adoption.":[194]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2026-03-12T00:00:00"}