{"id":"https://openalex.org/W7156007452","doi":"https://doi.org/10.1145/3774904.3792464","title":"Disentangled Graph LLM for Molecule Graph Editing under Distribution Shifts","display_name":"Disentangled Graph LLM for Molecule Graph Editing under Distribution Shifts","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7156007452","doi":"https://doi.org/10.1145/3774904.3792464"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792464","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792464","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792464","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100305724","display_name":"Yang Yao","orcid":"https://orcid.org/0000-0002-7975-3405"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yao","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-8733-7721","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0351-2939","affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103072786","display_name":"Yuan Meng","orcid":"https://orcid.org/0000-0002-7450-9438"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Meng","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7450-9438","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086592862","display_name":"Zeyang Zhang","orcid":"https://orcid.org/0000-0003-1329-1313"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyang Zhang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1329-1313","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633784","display_name":"Hong Mei","orcid":"https://orcid.org/0000-0003-2380-3976"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Mei","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2380-3976","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2236-9290","affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41507075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1149","last_page":"1159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.34139999747276306,"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":0.34139999747276306,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.2994000017642975,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.03739999979734421,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5996000170707703},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5884000062942505},{"id":"https://openalex.org/keywords/comparability-graph","display_name":"Comparability graph","score":0.49900001287460327},{"id":"https://openalex.org/keywords/graph-property","display_name":"Graph property","score":0.37779998779296875},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.3653999865055084},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.32589998841285706},{"id":"https://openalex.org/keywords/directed-graph","display_name":"Directed graph","score":0.3102000057697296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895999908447266},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5845000147819519},{"id":"https://openalex.org/C198414033","wikidata":"https://www.wikidata.org/wiki/Q5155607","display_name":"Comparability graph","level":5,"score":0.49900001287460327},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.37779998779296875},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C17169500","wikidata":"https://www.wikidata.org/wiki/Q3033506","display_name":"Null graph","level":5,"score":0.30329999327659607},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C145580432","wikidata":"https://www.wikidata.org/wiki/Q6497118","display_name":"Lattice graph","level":5,"score":0.2653000056743622},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792464","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792464","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792464","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792464","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2151697120","https://openalex.org/W2937307539","https://openalex.org/W2968734407","https://openalex.org/W4211216833","https://openalex.org/W4387561528","https://openalex.org/W4389888290","https://openalex.org/W4396945188","https://openalex.org/W4399880627","https://openalex.org/W4399911431","https://openalex.org/W4399912177","https://openalex.org/W4401306886","https://openalex.org/W4402667063","https://openalex.org/W4402671841","https://openalex.org/W4402702936","https://openalex.org/W4402915290","https://openalex.org/W4403882547","https://openalex.org/W4407764194"],"related_works":[],"abstract_inverted_index":{"Molecule":[0],"graph":[1,65,98,104,126,233],"editing":[2,66,87,105,108,195],"has":[3],"become":[4],"a":[5,96,124,159,169,176,217],"powerful":[6],"paradigm":[7],"for":[8,102],"optimizing":[9],"chemical":[10],"compounds":[11],"in":[12,47,59,231],"drug":[13],"discovery.":[14],"Existing":[15],"methods":[16],"overlook":[17],"the":[18,42,56,77,86,150,156],"invariant":[19,57,78,115],"structure-property":[20],"relationships,":[21],"and":[22,54,79,206,212],"rely":[23],"on":[24,193,216],"variable":[25],"correlations":[26],"that":[27,76,106,117,131,143,182,190,221],"shift":[28],"across":[29,146],"different":[30],"instructions,":[31],"thereby":[32],"failing":[33],"to":[34,36,52,61,187,225],"generalize":[35],"out-of-distribution":[37],"(O.O.D.)":[38],"scenarios.":[39],"To":[40,89],"overcome":[41],"weakness":[43],"of":[44],"existing":[45],"work,":[46],"this":[48,71,91],"paper":[49],"we":[50,93,122,154,174],"propose":[51,94,123],"capture":[53],"utilize":[55],"factors":[58,81,116],"order":[60],"achieve":[62,226],"generalizable":[63],"molecule":[64,103,232],"under":[67,110],"distribution":[68,111],"shifts.":[69],"However,":[70],"problem":[72],"remains":[73],"challenging,":[74],"given":[75],"variant":[80],"are":[82],"deeply":[83],"entangled":[84],"within":[85],"models.":[88],"tackle":[90],"challenge,":[92],"MoFE,":[95],"disentangled":[97,125,136],"large":[99],"language":[100],"model":[101,200],"handles":[107],"instructions":[109],"shifts":[112],"via":[113],"disentangling":[114],"govern":[118],"editing-relevant":[119],"properties.":[120],"Specifically,":[121],"projector":[127],"with":[128,139,149,158,168],"invariance":[129,141],"loss":[130,142,179],"encodes":[132],"molecular":[133],"graphs":[134],"into":[135],"latent":[137,171,207],"factors,":[138,208],"an":[140],"ensures":[144],"consistency":[145],"paraphrased":[147],"prompts":[148],"same":[151],"objective.":[152],"Then,":[153],"enhance":[155],"LLM":[157],"factor-aware":[160],"LoRA":[161],"mixture-of-experts,":[162],"where":[163],"each":[164],"expert":[165],"is":[166,223],"associated":[167],"distinct":[170],"factor.":[172],"Additionally,":[173],"introduce":[175],"factor":[177],"disentanglement":[178,203],"weighting":[180],"strategy":[181],"adaptively":[183],"assigns":[184],"higher":[185],"weights":[186],"expert-factor":[188],"pairs":[189],"perform":[191],"well":[192],"relevant":[194],"tasks.":[196],"The":[197],"proposed":[198],"MoFE":[199,222],"promotes":[201],"joint":[202],"between":[204],"experts":[205],"reinforcing":[209],"their":[210],"alignment":[211],"preventing":[213],"collapse.":[214],"Experiments":[215],"representative":[218],"benchmark":[219],"demonstrate":[220],"able":[224],"superior":[227],"O.O.D.":[228],"generalization":[229],"performance":[230],"editing.":[234]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-28T00:00:00"}