{"id":"https://openalex.org/W4408352000","doi":"https://doi.org/10.1109/icassp49660.2025.10888554","title":"Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models","display_name":"Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models","alternate_titles":[],"publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352000","doi":"https://doi.org/10.1109/icassp49660.2025.10888554"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888554","doi":"https://doi.org/10.1109/icassp49660.2025.10888554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4408352000"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.19128","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070124654","display_name":"Yize Li","orcid":"https://orcid.org/0000-0003-1074-281X","observed_orcids":["https://orcid.org/0000-0003-1074-281X"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Yize Li","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering,Boston,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering,Boston,USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407083","display_name":"Yihua Zhang","orcid":"https://orcid.org/0000-0002-5147-9838","observed_orcids":["https://orcid.org/0000-0002-5147-9838"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Yihua Zhang","raw_affiliation_strings":["Michigan State University,Department of Computer Science and Engineering,East Lansing,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University,Department of Computer Science and Engineering,East Lansing,USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321842","display_name":"Sijia Liu","orcid":"https://orcid.org/0000-0003-2169-8586","observed_orcids":["https://orcid.org/0000-0003-2169-8586"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Sijia Liu","raw_affiliation_strings":["Michigan State University,Department of Computer Science and Engineering,East Lansing,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University,Department of Computer Science and Engineering,East Lansing,USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043582832","display_name":"Xue Lin","orcid":"https://orcid.org/0000-0001-6210-8883","observed_orcids":["https://orcid.org/0000-0001-6210-8883"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Xue Lin","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering,Boston,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering,Boston,USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3168,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95205068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":86,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0008999999845400453,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0003000000142492354,"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/diffusion-models","display_name":"diffusion models","score":0.8389999866485596},{"id":"https://openalex.org/keywords/data-efficient-training","display_name":"data-efficient training","score":0.9399999976158142},{"id":"https://openalex.org/keywords/dataset-pruning","display_name":"dataset pruning","score":0.9380000233650208},{"id":"https://openalex.org/keywords/coreset-selection","display_name":"coreset selection","score":0.9160000085830688},{"id":"https://openalex.org/keywords/dataset-selection","display_name":"data selection","score":0.6779999732971191},{"id":"https://openalex.org/keywords/distributionally-robust-optimization","display_name":"distributionally robust optimization","score":0.8240000009536743},{"id":"https://openalex.org/keywords/surrogate-modeling","display_name":"surrogate models","score":0.5070000290870667},{"id":"https://openalex.org/keywords/denoising-diffusion-probabilistic-models","display_name":"denoising diffusion probabilistic models","score":0.6669999957084656},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.9660000205039978},{"id":"https://openalex.org/keywords/stable-diffusion","display_name":"Stable Diffusion","score":0.9860000014305115},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.5960000157356262},{"id":"https://openalex.org/keywords/training-efficiency","display_name":"training efficiency","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7661356329917908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7370442748069763},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6123338937759399},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5222521424293518},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5148178935050964},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5048823952674866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.445991575717926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3769993782043457},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12642663717269897},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888554","doi":"https://doi.org/10.1109/icassp49660.2025.10888554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.19128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.19128","pdf_url":"https://arxiv.org/pdf/2409.19128","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.19128","doi":"https://doi.org/10.48550/arxiv.2409.19128","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.19128","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.19128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.19128","pdf_url":"https://arxiv.org/pdf/2409.19128","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408352000.pdf","grobid_xml":"https://content.openalex.org/works/W4408352000.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2904367110","https://openalex.org/W2962785568","https://openalex.org/W2963981733","https://openalex.org/W2991497298","https://openalex.org/W3032949543","https://openalex.org/W3036167779","https://openalex.org/W3045501090","https://openalex.org/W3092442149","https://openalex.org/W3110257065","https://openalex.org/W3135367836","https://openalex.org/W3162926177","https://openalex.org/W3177900337","https://openalex.org/W4221159371","https://openalex.org/W4221160862","https://openalex.org/W4281258849","https://openalex.org/W4283073619","https://openalex.org/W4285981784","https://openalex.org/W4288099666","https://openalex.org/W4312933868","https://openalex.org/W4322759334","https://openalex.org/W4323921995","https://openalex.org/W4380558692","https://openalex.org/W4380994510","https://openalex.org/W4386047807","https://openalex.org/W4386071831","https://openalex.org/W4386722101","https://openalex.org/W4388994505","https://openalex.org/W4390872010","https://openalex.org/W4390872297","https://openalex.org/W4390873030","https://openalex.org/W4390873054","https://openalex.org/W4390873332","https://openalex.org/W4390874529","https://openalex.org/W4390874580","https://openalex.org/W4393300257","https://openalex.org/W4400315380","https://openalex.org/W4402585403","https://openalex.org/W4402715897","https://openalex.org/W4402726956","https://openalex.org/W4402727293","https://openalex.org/W4402753907","https://openalex.org/W4402778510","https://openalex.org/W4403888423","https://openalex.org/W6784333009","https://openalex.org/W6796435857","https://openalex.org/W6838327568","https://openalex.org/W6861887733","https://openalex.org/W7133193464","https://openalex.org/W7133198842","https://openalex.org/W7133211181","https://openalex.org/W7133216852","https://openalex.org/W7133218093","https://openalex.org/W7133233455","https://openalex.org/W7163131497"],"related_works":["https://openalex.org/W7133233455","https://openalex.org/W4402660129","https://openalex.org/W4415330435","https://openalex.org/W4404573977","https://openalex.org/W4408352570","https://openalex.org/W7133211181","https://openalex.org/W4417172947","https://openalex.org/W4413146340","https://openalex.org/W4415796383","https://openalex.org/W7048890007"],"abstract_inverted_index":{"Despite":[0],"the":[1,43,50,67,95,100,132,150,156],"remarkable":[2],"generation":[3,101,184],"capabilities":[4],"of":[5,45,52,134,149],"Diffusion":[6,174,179],"Models":[7],"(DMs),":[8],"conducting":[9],"training":[10,29,41,54],"and":[11,86,140,160,177,181],"inference":[12],"remains":[13],"computationally":[14],"expensive.":[15],"Previous":[16],"works":[17],"have":[18],"been":[19,32],"devoted":[20],"to":[21,74,93,147,168],"accelerating":[22],"diffusion":[23,28,40],"sampling,":[24],"but":[25],"achieving":[26,155],"data-efficient":[27,53],"has":[30],"often":[31],"overlooked.":[33],"In":[34],"this":[35],"work,":[36],"we":[37,64,103],"investigate":[38],"efficient":[39],"from":[42],"perspective":[44],"dataset":[46],"pruning.":[47],"Inspired":[48],"by":[49,82],"principles":[51],"for":[55],"generative":[56,60],"models":[57],"such":[58],"as":[59],"adversarial":[61],"networks":[62],"(GANs),":[63],"first":[65],"extend":[66],"data":[68,78],"selection":[69],"scheme":[70],"used":[71],"in":[72,143],"GANs":[73],"DM":[75,126],"training,":[76],"where":[77],"features":[79],"are":[80],"encoded":[81],"a":[83,87,105,119,124],"surrogate":[84],"model,":[85],"score":[88],"criterion":[89],"is":[90],"then":[91],"applied":[92],"select":[94],"coreset.":[96],"To":[97],"further":[98],"improve":[99],"performance,":[102],"employ":[104],"class-wise":[106],"reweighting":[107],"approach,":[108],"which":[109],"derives":[110],"class":[111],"weights":[112],"through":[113],"distributionally":[114],"robust":[115],"optimization":[116],"(DRO)":[117],"over":[118,137],"pre-trained":[120],"reference":[121],"DM.":[122],"For":[123],"pixel-wise":[125],"(DDPM)":[127],"on":[128,186],"CIFAR-10,":[129],"experiments":[130],"demonstrate":[131],"superiority":[133],"our":[135,163],"methodology":[136],"existing":[138],"approaches":[139],"its":[141],"effectiveness":[142],"image":[144],"synthesis":[145],"comparable":[146],"that":[148],"original":[151],"full-data":[152],"model":[153],"while":[154],"speed-up":[157],"between":[158],"2.34\u00d7":[159],"8.32\u00d7.":[161],"Additionally,":[162],"method":[164],"could":[165],"be":[166],"generalized":[167],"latent":[169],"DMs":[170],"(LDMs),":[171],"e.g.,":[172],"Masked":[173],"Transformer":[175],"(MDT)":[176],"Stable":[178],"(SD),":[180],"achieves":[182],"competitive":[183],"capability":[185],"ImageNet.":[187]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4408352000","counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2025-03-13T00:00:00"}
