{"id":"https://openalex.org/W7147557419","doi":"https://doi.org/10.48550/arxiv.2603.29768","title":"Big2Small: A Unifying Neural Network Framework for Model Compression","display_name":"Big2Small: A Unifying Neural Network Framework for Model Compression","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147557419","doi":"https://doi.org/10.48550/arxiv.2603.29768"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29768","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29768","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050878071","display_name":"Jing-Xiao Liao","orcid":"https://orcid.org/0000-0002-1880-2621"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Jing-Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132703979","display_name":"Haoran Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132665009","display_name":"Tao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025744129","display_name":"Daoming Lyu","orcid":"https://orcid.org/0000-0003-2625-9865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Daoming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132730662","display_name":"Yi Wen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060364496","display_name":"Chengjun Cai","orcid":"https://orcid.org/0000-0002-8045-4226"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Chengjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132651214","display_name":"Feng-Lei Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Feng-Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.43470001220703125,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.43470001220703125,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.20990000665187836,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.05490000173449516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5950999855995178},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5616999864578247},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5415999889373779},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4584999978542328},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.41499999165534973},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.41019999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661899983882904},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977000057697296},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.41499999165534973},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.39100000262260437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.25119999051094055},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29768","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.29768","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"With":[0],"the":[1,40,107,118,125],"development":[2],"of":[3,109,120],"foundational":[4],"models,":[5],"model":[6,14,55,66,92],"compression":[7,15,56,67,93,164],"has":[8],"become":[9],"a":[10,45,50,73,78,143],"critical":[11],"requirement.":[12],"Various":[13],"approaches":[16],"have":[17],"been":[18],"proposed":[19],"such":[20],"as":[21],"low-rank":[22],"decomposition,":[23],"pruning,":[24],"quantization,":[25],"ergodic":[26],"dynamic":[27],"systems,":[28],"and":[29,84,123,142,155,163],"knowledge":[30],"distillation,":[31],"which":[32,97],"are":[33],"based":[34],"on":[35,152],"different":[36],"heuristics.":[37],"To":[38,129],"elevate":[39],"field":[41],"from":[42,103],"fragmentation":[43],"to":[44,72,77,106,116,137,147,167],"principled":[46],"discipline,":[47],"we":[48,87,133],"construct":[49],"unifying":[51],"mathematical":[52,83],"framework":[53],"for":[54],"grounded":[57],"in":[58],"measure":[59],"theory.":[60],"We":[61],"further":[62],"demonstrate":[63,157],"that":[64,158],"each":[65],"technique":[68],"is":[69],"mathematically":[70],"equivalent":[71],"neural":[74],"network":[75,110],"subject":[76],"regularization.":[79],"Building":[80],"upon":[81],"this":[82],"structural":[85],"equivalence,":[86],"propose":[88],"an":[89],"experimentally-verified":[90],"data-free":[91],"framework,":[94],"termed":[95],"\\textit{Big2Small},":[96],"translates":[98],"Implicit":[99],"Neural":[100],"Representations":[101],"(INRs)":[102],"data":[104],"domain":[105,108],"parameters.":[111],"\\textit{Big2Small}":[112,159],"trains":[113],"compact":[114],"INRs":[115],"encode":[117],"weights":[119,126],"larger":[121],"models":[122],"reconstruct":[124],"during":[127],"inference.":[128],"enhance":[130],"reconstruction":[131],"fidelity,":[132],"introduce":[134],"Outlier-Aware":[135],"Preprocessing":[136],"handle":[138],"extreme":[139],"weight":[140],"values":[141],"Frequency-Aware":[144],"Loss":[145],"function":[146],"preserve":[148],"high-frequency":[149],"details.":[150],"Experiments":[151],"image":[153],"classification":[154],"segmentation":[156],"achieves":[160],"competitive":[161],"accuracy":[162],"ratios":[165],"compared":[166],"state-of-the-art":[168],"baselines.":[169]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}