{"id":"https://openalex.org/W4414359301","doi":"https://doi.org/10.24963/ijcai.2025/818","title":"FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers","display_name":"FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359301","doi":"https://doi.org/10.24963/ijcai.2025/818"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/818","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5017433485","display_name":"Tianyu Chen","orcid":"https://orcid.org/0000-0001-7056-2947"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyu Chen","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086419494","display_name":"Haoyi Zhou","orcid":"https://orcid.org/0000-0002-2393-3634"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Zhou","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785618","display_name":"Ying Li","orcid":"https://orcid.org/0000-0001-8438-6999"},"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":"Ying Li","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101854659","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-6959-7237"},"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":"Hao Wang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102810323","display_name":"Zhenzhe Zhang","orcid":"https://orcid.org/0009-0005-3619-9781"},"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":"Zhenzhe Zhang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024079569","display_name":"Tianchen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianchen Zhu","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013030532","display_name":"Shanghang Zhang","orcid":"https://orcid.org/0000-0003-4047-3526"},"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":"Shanghang Zhang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380463","display_name":"Jianxin Li","orcid":"https://orcid.org/0000-0001-5152-0055"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Li","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5017433485"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21161443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7356","last_page":"7364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.6201000213623047,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.6201000213623047,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.6186000108718872,"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/dependency","display_name":"Dependency (UML)","score":0.6305000185966492},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6274999976158142},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.6176000237464905},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5760999917984009},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5001000165939331},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43869999051094055},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.420199990272522},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.4097000062465668}],"concepts":[{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6288999915122986},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5396000146865845},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.398499995470047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33550000190734863},{"id":"https://openalex.org/C8590192","wikidata":"https://www.wikidata.org/wiki/Q1054694","display_name":"Frequency response","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C176321772","wikidata":"https://www.wikidata.org/wiki/Q1430640","display_name":"Numerical stability","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3073999881744385},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C156439662","wikidata":"https://www.wikidata.org/wiki/Q7573793","display_name":"Sparse grid","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C104942944","wikidata":"https://www.wikidata.org/wiki/Q3434686","display_name":"Truncation error","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C21905445","wikidata":"https://www.wikidata.org/wiki/Q5502873","display_name":"Frequency grid","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/818","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fourier":[0],"Neural":[1],"Operators":[2],"(FNO)":[3],"have":[4],"emerged":[5],"as":[6,50],"promising":[7],"solutions":[8],"for":[9,34,170],"efficiently":[10],"solving":[11,171],"partial":[12],"differential":[13],"equations":[14],"(PDEs)":[15],"by":[16],"learning":[17],"infinite-dimensional":[18],"function":[19],"mappings":[20],"through":[21],"frequency":[22,101,164,167],"domain":[23],"transformations.":[24],"However,":[25],"the":[26,71,100,105,142],"sparsity":[27],"of":[28,73,96],"high-frequency":[29,42,74,109],"signals":[30,75],"limits":[31],"computational":[32],"efficiency":[33],"high-dimensional":[35],"inputs,":[36],"and":[37,65,85,115,150,157],"fixed-pattern":[38],"truncation":[39],"often":[40],"causes":[41],"signal":[43],"loss,":[44],"reducing":[45],"performance":[46],"in":[47,99,147],"scenarios":[48],"such":[49],"high-resolution":[51],"inputs":[52],"or":[53],"long-term":[54,148],"predictions.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"we":[60],"propose":[61],"FreqMoE,":[62],"an":[63],"efficient":[64],"progressive":[66],"training":[67],"framework":[68],"that":[69,120],"exploits":[70],"dependency":[72],"on":[76,112],"low-frequency":[77,83],"components.":[78],"The":[79],"model":[80],"first":[81],"learns":[82],"weights":[84,107],"then":[86],"applies":[87],"a":[88,94,161],"sparse":[89],"upward-cycling":[90],"strategy":[91],"to":[92,108,124,138,153],"construct":[93],"mixture":[95],"experts":[97],"(MoE)":[98],"domain,":[102],"effectively":[103],"extending":[104],"learned":[106],"regions.":[110],"Experiments":[111],"both":[113],"regular":[114],"irregular":[116],"grid":[117,158],"PDEs":[118],"demonstrate":[119],"FreqMoE":[121],"achieves":[122],"up":[123],"16.6":[125],"percent":[126,133],"accuracy":[127],"improvement":[128],"while":[129],"using":[130],"merely":[131],"2.1":[132],"parameters":[134],"(47.32x":[135],"reduction)":[136],"compared":[137],"dense":[139],"FNO.":[140],"Furthermore,":[141],"approach":[143],"demonstrates":[144],"remarkable":[145],"stability":[146],"predictions":[149],"generalizes":[151],"seamlessly":[152],"various":[154],"FNO":[155],"variants":[156],"structures,":[159],"establishing":[160],"new":[162],"Low":[163],"Pretraining,":[165],"High":[166],"Fine-tuning''":[168],"paradigm":[169],"PDEs.":[172]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}