{"id":"https://openalex.org/W4416920057","doi":"https://doi.org/10.1145/3737898.3769042","title":"The Early Prune Catches the Model: Enhancing CNN Training Efficiency with Early-Epoch Pruning","display_name":"The Early Prune Catches the Model: Enhancing CNN Training Efficiency with Early-Epoch Pruning","publication_year":2025,"publication_date":"2025-11-04","ids":{"openalex":"https://openalex.org/W4416920057","doi":"https://doi.org/10.1145/3737898.3769042"},"language":null,"primary_location":{"id":"doi:10.1145/3737898.3769042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3737898.3769042","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3737898.3769042","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 16th ACM Workshop on Wireless of the Students, by the Students, for the Students","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3737898.3769042","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109350636","display_name":"M. Fiaz Khan","orcid":"https://orcid.org/0009-0001-5259-6331"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Musfira Khan","raw_affiliation_strings":["University of Helsinki Helsinki, Finland"],"raw_orcid":"https://orcid.org/0009-0001-5259-6331","affiliations":[{"raw_affiliation_string":"University of Helsinki Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054275085","display_name":"Agustin Zuniga","orcid":"https://orcid.org/0000-0002-6481-3559"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Agustin Zuniga","raw_affiliation_strings":["University of Helsinki Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0002-6481-3559","affiliations":[{"raw_affiliation_string":"University of Helsinki Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054443906","display_name":"Sasu Tarkoma","orcid":"https://orcid.org/0000-0003-4220-3650"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sasu Tarkoma","raw_affiliation_strings":["University of Helsinki Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0003-4220-3650","affiliations":[{"raw_affiliation_string":"University of Helsinki Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066542585","display_name":"Petteri Nurmi","orcid":"https://orcid.org/0000-0001-8262-6434"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Petteri Nurmi","raw_affiliation_strings":["University of Helsinki Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0001-8262-6434","affiliations":[{"raw_affiliation_string":"University of Helsinki Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6155999898910522,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6155999898910522,"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":0.08630000054836273,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.061400000005960464,"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/pruning","display_name":"Pruning","score":0.836899995803833},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.635200023651123},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5809000134468079},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.49779999256134033},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44600000977516174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4300000071525574},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3889000117778778}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.836899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759999990463257},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.635200023651123},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5809000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5734000205993652},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.527999997138977},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3737898.3769042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3737898.3769042","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3737898.3769042","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 16th ACM Workshop on Wireless of the Students, by the Students, for the Students","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3737898.3769042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3737898.3769042","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3737898.3769042","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 16th ACM Workshop on Wireless of the Students, by the Students, for the Students","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6219495610","display_name":null,"funder_award_id":"339614","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G8184908717","display_name":"Foundations of Pervasive Sensing Systems","funder_award_id":"339614","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416920057.pdf","grobid_xml":"https://content.openalex.org/works/W4416920057.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2928560789","https://openalex.org/W2962851801","https://openalex.org/W2965862774","https://openalex.org/W4226038224"],"related_works":[],"abstract_inverted_index":{"Pruning":[0],"convolutional":[1],"neural":[2],"networks":[3],"traditionally":[4],"involves":[5],"computing":[6],"channel":[7],"importance":[8,59],"scores":[9],"after":[10,49],"the":[11,42,82,106],"model":[12,51,101,117],"has":[13],"been":[14],"fully":[15],"trained,":[16],"a":[17,30,97,112],"process":[18],"that":[19,86],"is":[20],"both":[21],"time-consuming":[22],"and":[23,69],"resource-intensive.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"contribute":[29],"comparative":[31],"study":[32],"of":[33,57,108],"early-epoch":[34,87],"pruning,":[35],"where":[36],"pruning":[37,47,58,88,110],"decisions":[38],"are":[39],"made":[40],"during":[41],"training":[43],"process,":[44],"against":[45],"conventional":[46],"conducted":[48,78],"full":[50],"training.":[52],"We":[53],"evaluate":[54],"two":[55],"classes":[56],"criteria:":[60],"structural":[61],"metrics,":[62,71],"represented":[63,72],"by":[64,73],"batch":[65],"normalization":[66],"scale":[67],"magnitudes,":[68],"data-driven":[70],"weight":[74],"activations.":[75],"Our":[76,103],"experiments,":[77],"on":[79],"ResNet-10":[80],"using":[81],"CIFAR-10":[83],"dataset,":[84],"demonstrate":[85],"can":[89],"yield":[90],"significant":[91],"resource":[92],"savings":[93],"while":[94],"incurring":[95],"only":[96],"moderate":[98],"loss":[99],"in":[100],"accuracy.":[102],"work":[104],"demonstrates":[105],"potential":[107],"early":[109],"as":[111,124],"practical":[113],"approach":[114],"to":[115],"accelerate":[116],"training,":[118],"particularly":[119],"for":[120],"resource-constrained":[121],"environments":[122],"such":[123],"edge":[125],"devices.":[126]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-02T00:00:00"}