{"id":"https://openalex.org/W4401863323","doi":"https://doi.org/10.1145/3637528.3671886","title":"Advancing Molecule Invariant Representation via Privileged Substructure Identification","display_name":"Advancing Molecule Invariant Representation via Privileged Substructure Identification","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863323","doi":"https://doi.org/10.1145/3637528.3671886"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5101813137","display_name":"Ruijia Wang","orcid":"https://orcid.org/0000-0003-2294-9164"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijia Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications & China Telecom Cloud Computing Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2294-9164","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications & China Telecom Cloud Computing Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113348028","display_name":"H. X. Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Dai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0428-4285","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060417049","display_name":"Cheng Yang","orcid":"https://orcid.org/0000-0001-7821-0030"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7821-0030","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030589527","display_name":"Le Song","orcid":"https://orcid.org/0000-0002-9655-2787"},"institutions":[{"id":"https://openalex.org/I4210140416","display_name":"New England Biolabs (China)","ror":"https://ror.org/03nb3ch98","country_code":"CN","type":"company","lineage":["https://openalex.org/I115020962","https://openalex.org/I4210140416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Song","raw_affiliation_strings":["BioMap Research & MBZUAI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9655-2787","affiliations":[{"raw_affiliation_string":"BioMap Research & MBZUAI, Beijing, China","institution_ids":["https://openalex.org/I4210140416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705849","display_name":"Chuan Shi","orcid":"https://orcid.org/0000-0002-3734-0266"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Shi","raw_affiliation_strings":["Beijing University of Post and Telecommunication, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3734-0266","affiliations":[{"raw_affiliation_string":"Beijing University of Post and Telecommunication, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3205,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61442281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3188","last_page":"3199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9997000098228455,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9775000214576721,"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/substructure","display_name":"Substructure","score":0.6990422010421753},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6973318457603455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5584685802459717},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5207114815711975},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5184466242790222},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4620944559574127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4401799440383911},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32718968391418457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21076518297195435},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12780341506004333}],"concepts":[{"id":"https://openalex.org/C99679407","wikidata":"https://www.wikidata.org/wiki/Q56761637","display_name":"Substructure","level":2,"score":0.6990422010421753},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6973318457603455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5584685802459717},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5207114815711975},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5184466242790222},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4620944559574127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4401799440383911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32718968391418457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21076518297195435},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12780341506004333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1983478747","https://openalex.org/W1988037271","https://openalex.org/W2022476850","https://openalex.org/W2107081909","https://openalex.org/W2200017991","https://openalex.org/W2472954632","https://openalex.org/W2765407302","https://openalex.org/W2894728917","https://openalex.org/W2964288524","https://openalex.org/W2968734407","https://openalex.org/W2994728899","https://openalex.org/W2998101974","https://openalex.org/W2998653622","https://openalex.org/W3021975806","https://openalex.org/W3087318293","https://openalex.org/W3095883070","https://openalex.org/W3100078588","https://openalex.org/W3109916301","https://openalex.org/W3116637551","https://openalex.org/W3127113723","https://openalex.org/W3153206160","https://openalex.org/W3168441138","https://openalex.org/W3204222276","https://openalex.org/W4200635484","https://openalex.org/W4236463097","https://openalex.org/W4282004119","https://openalex.org/W4283752247","https://openalex.org/W4290948450","https://openalex.org/W4297969478","https://openalex.org/W4304984779","https://openalex.org/W4309793942","https://openalex.org/W4320476363","https://openalex.org/W4382458099","https://openalex.org/W6600291067","https://openalex.org/W6637618735"],"related_works":["https://openalex.org/W3153444835","https://openalex.org/W2153916713","https://openalex.org/W2023846184","https://openalex.org/W2703419385","https://openalex.org/W2329056228","https://openalex.org/W2284584236","https://openalex.org/W2950955148","https://openalex.org/W1979083399","https://openalex.org/W4386136067","https://openalex.org/W4286858940"],"abstract_inverted_index":{"Graph":[0],"neural":[1,159],"networks":[2],"(GNNs)":[3],"have":[4],"revolutionized":[5],"molecule":[6,102,120,147,201],"representation":[7],"learning":[8,122,203],"by":[9,151],"modeling":[10],"molecules":[11,40],"as":[12,17,22,33],"graphs,":[13],"with":[14,29,41,101],"atoms":[15],"represented":[16],"nodes":[18],"and":[19,80,95,128,169,177,190,204,213],"chemical":[20],"bonds":[21],"edges.":[23],"Despite":[24],"their":[25],"progress,":[26],"they":[27],"struggle":[28],"out-of-distribution":[30],"scenarios,":[31],"such":[32],"changes":[34],"in":[35,66],"size":[36],"or":[37],"scaffold":[38],"of":[39,69,183,224],"identical":[42],"properties.":[43],"Some":[44],"studies":[45],"attempt":[46],"to":[47,61,146,192,227],"mitigate":[48],"this":[49,92,107,135],"issue":[50],"through":[51],"graph":[52,158],"invariant":[53,63,82,103,121,148,202],"learning,":[54],"which":[55],"penalizes":[56],"prediction":[57],"variance":[58],"across":[59,83,218],"environments":[60,187],"learn":[62],"representations.":[64],"But":[65],"the":[67,88,97,181,186,222],"realm":[68],"molecules,":[70],"core":[71],"functional":[72],"groups":[73],"forming":[74],"privileged":[75,125,165,178],"substructures":[76],"dominate":[77],"molecular":[78],"properties":[79],"remain":[81],"distribution":[84],"shifts.":[85],"This":[86],"highlights":[87],"need":[89],"for":[90,142],"integrating":[91],"prior":[93],"knowledge":[94],"ensuring":[96],"environment":[98,143,168,205],"split":[99,189,206],"compatible":[100],"learning.":[104,149],"To":[105],"bridge":[106],"gap,":[108],"we":[109,117,137,154],"propose":[110],"a":[111,156],"novel":[112],"framework":[113],"named":[114],"MILI.":[115],"Specifically,":[116],"first":[118],"formalize":[119],"based":[123,174],"on":[124,134,175],"substructure":[126,130],"identification":[127],"introduce":[129],"invariance":[131],"constraint.":[132],"Building":[133],"foundation,":[136],"theoretically":[138],"establish":[139],"two":[140,184],"criteria":[141],"splits":[144],"conducive":[145],"Inspired":[150],"these":[152],"criteria,":[153],"develop":[155],"dual-head":[157],"network.":[160],"A":[161],"shared":[162],"identifier":[163],"identifies":[164],"substructures,":[166],"while":[167],"task":[170],"heads":[171],"generate":[172],"predictions":[173],"variant":[176],"substructures.":[179],"Through":[180],"interaction":[182],"heads,":[185],"are":[188],"optimized":[191],"meet":[193],"our":[194],"criteria.":[195],"The":[196],"unified":[197],"MILI":[198,225],"guarantees":[199],"that":[200],"achieve":[207],"mutual":[208],"enhancement":[209],"from":[210],"theoretical":[211],"analysis":[212],"network":[214],"design.":[215],"Extensive":[216],"experiments":[217],"eight":[219],"benchmarks":[220],"validate":[221],"effectiveness":[223],"compared":[226],"state-of-the-art":[228],"baselines.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}