{"id":"https://openalex.org/W7133541754","doi":"https://doi.org/10.1145/3800575","title":"MoEPlan: A Lazy Learned Query-Selection Optimizer via Mixture of Optimizer Experts","display_name":"MoEPlan: A Lazy Learned Query-Selection Optimizer via Mixture of Optimizer Experts","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7133541754","doi":"https://doi.org/10.1145/3800575"},"language":"en","primary_location":{"id":"doi:10.1145/3800575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3800575","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-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/A5128060210","display_name":"Suchen Liu","orcid":null},"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":"Suchen Liu","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies, CS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2580-8068","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies, CS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128125990","display_name":"Jun Gao","orcid":null},"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":"Jun Gao","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies, CS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6750-8496","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies, CS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128064276","display_name":"Yinjun Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinjun Han","raw_affiliation_strings":["ZTE Corporation, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5578-2351","affiliations":[{"raw_affiliation_string":"ZTE Corporation, Nanjing, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112114867","display_name":"Yang Lin","orcid":"https://orcid.org/0009-0007-8658-0016"},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Lin","raw_affiliation_strings":["ZTE Corporation, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-8658-0016","affiliations":[{"raw_affiliation_string":"ZTE Corporation, Nanjing, China","institution_ids":["https://openalex.org/I4210098582"]}]}],"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":0.21557254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.23270000517368317,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.23270000517368317,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.11980000138282776,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.11479999870061874,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/inference","display_name":"Inference","score":0.6381999850273132},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.614799976348877},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47510001063346863},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.42730000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979999780654907},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6381999850273132},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6287999749183655},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.614799976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462999939918518},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2793000042438507}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3800575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3800575","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7464771943","display_name":null,"funder_award_id":"62272008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2066623874","https://openalex.org/W2077902449","https://openalex.org/W2112420033","https://openalex.org/W2123083497","https://openalex.org/W2150884987","https://openalex.org/W2282866165","https://openalex.org/W2907492528","https://openalex.org/W2911464154","https://openalex.org/W2963355447","https://openalex.org/W2970148517","https://openalex.org/W3029535034","https://openalex.org/W3097225903","https://openalex.org/W4206547457","https://openalex.org/W4221142004","https://openalex.org/W4283326127","https://openalex.org/W4312869703","https://openalex.org/W4386128230","https://openalex.org/W7133237023"],"related_works":[],"abstract_inverted_index":{"Learned":[0],"plan-selection":[1,180],"optimizers":[2,16],"combine":[3],"the":[4,19,38,85,102,111,124,128,135,139,150,154],"conventional":[5],"and":[6,17,64,93,105,148],"learned":[7,90,179],"approaches":[8],"by":[9],"generating":[10],"diverse":[11],"candidate":[12,70],"plans":[13,27,109,165,176],"through":[14,89],"multiple":[15,35],"selecting":[18],"best":[20,86],"via":[21,61],"value":[22],"models.":[23],"However,":[24],"these":[25],"eagerly-generated":[26],"incur":[28],"high":[29],"optimization":[30,76],"overhead,":[31],"as":[32],"they":[33],"require":[34],"invocations":[36],"of":[37,69,107,114],"native":[39],"optimizer.":[40],"In":[41],"this":[42],"article,":[43],"we":[44,118],"propose":[45],"MoEPlan,":[46,161],"which":[47],"learns":[48],"a":[49,79,95,120,145],"routing":[50],"policy":[51],"to":[52,83,100,143,152],"select":[53],"top-":[54],"\\(":[55],"k":[56],"\\)":[57],"experts":[58],"(different":[59],"optimizers)":[60],"query":[62],"embedding":[63],"learnable":[65],"parameters,":[66],"avoiding":[67],"pre-generation":[68],"plans.":[71],"Our":[72],"approach":[73],"integrates":[74],"two":[75,164],"strategies:":[77],"(1)":[78],"virtual":[80],"ideal":[81],"expert":[82,97,115,132,141],"guide":[84],"plan":[87,91],"selection":[88,151],"similarities,":[92],"(2)":[94],"query-irrelevant":[96],"sampling":[98],"strategy":[99],"balance":[101],"training":[103,122],"cost":[104],"effectiveness":[106],"selected":[108],"in":[110],"first":[112,125],"round":[113],"selection.":[116],"Furthermore,":[117],"design":[119],"two-phase":[121],"process:":[123],"phase":[126,137],"pre-trains":[127],"model":[129],"with":[130,162],"complete":[131],"feedback,":[133],"while":[134,171],"second":[136],"filters":[138],"full":[140],"pool":[142],"yield":[144],"promising":[146],"subset":[147],"refines":[149],"pinpoint":[153],"optimal":[155],"expert.":[156],"Experimental":[157],"studies":[158],"show":[159],"that":[160],"only":[163],"generated,":[166],"takes":[167],"less":[168],"inference":[169],"time,":[170],"still":[172],"producing":[173],"more":[174],"efficient":[175],"than":[177],"other":[178],"optimizers.":[181]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-05T00:00:00"}