{"id":"https://openalex.org/W4415428495","doi":"https://doi.org/10.3233/faia251114","title":"Reinforcement Learning-Driven Model Compression: Structured Layer-Wise Parameter Pruning","display_name":"Reinforcement Learning-Driven Model Compression: Structured Layer-Wise Parameter Pruning","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428495","doi":"https://doi.org/10.3233/faia251114"},"language":null,"primary_location":{"id":"doi:10.3233/faia251114","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251114","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251114","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ashmit Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashmit Gupta","raw_affiliation_strings":["Department of Mathematics, Indian Institute of Technology Ropar, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology Ropar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000026972","display_name":"A. Dhamija","orcid":null},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anany Dhamija","raw_affiliation_strings":["Department of Mathematics, Indian Institute of Technology Ropar, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology Ropar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072895109","display_name":"Manik Gupta","orcid":"https://orcid.org/0000-0002-4977-4299"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manik Gupta","raw_affiliation_strings":["Department of Mathematics, Indian Institute of Technology Ropar, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology Ropar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120092240","display_name":"Parul Kukrety","orcid":null},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parul Kukrety","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003320528","display_name":"Shashi Shekhar Jha","orcid":"https://orcid.org/0000-0002-1375-2266"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashi Shekhar Jha","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055393595","display_name":"Sudeepta Mishra","orcid":"https://orcid.org/0000-0003-4821-4318"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudeepta Mishra","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119241673"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72514881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9075000286102295,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7533000111579895},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6769999861717224},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5631999969482422},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5277000069618225},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4862000048160553},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.4138999879360199},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4131999909877777},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.3743000030517578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734000086784363},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7533000111579895},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6769999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6686000227928162},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5631999969482422},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4334999918937683},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.313400000333786},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.27649998664855957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2678000032901764}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251114","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251114","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251114","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251114","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models,":[2],"albeit":[3],"having":[4],"remarkable":[5],"performance":[6,189],"in":[7,21,45,51,215,233],"various":[8],"image":[9],"and":[10,37,116,175,190,249],"vision":[11],"tasks,":[12],"are":[13,55],"notoriously":[14],"parameter-inefficient.":[15],"The":[16,96,139],"huge":[17],"number":[18],"of":[19,93,121,208,213,231],"parameters":[20,50],"these":[22],"models":[23,54,66,171],"makes":[24],"them":[25],"unsuitable":[26],"for":[27,67,219,247,254],"large-scale":[28],"deployment":[29,69],"on":[30,70,169],"resource-constrained":[31,71],"devices":[32],"due":[33],"to":[34,62,106,111,134],"high":[35],"memory":[36],"computational":[38],"requirements.":[39],"It":[40],"has":[41],"also":[42],"been":[43],"observed":[44],"the":[46,100,136,223,243],"literature":[47],"that":[48,88,158,181],"many":[49],"such":[52,172],"deep":[53,65,94,124],"redundant.":[56],"Hence,":[57],"there":[58],"is":[59],"a":[60,79,122,131,147,154,205,211,229],"need":[61],"extract":[63],"parameter-efficient":[64],"wide-scale":[68],"devices.":[72],"To":[73],"address":[74],"this":[75],"challenge,":[76],"we":[77,152,203,221],"propose":[78,153],"novel":[80],"parameter":[81],"reduction":[82],"framework":[83],"using":[84,143],"Reinforcement":[85],"Learning":[86],"(RL)":[87],"performs":[89],"layer-wise":[90],"structured":[91],"pruning":[92,137,197,244],"models.":[95],"proposed":[97,237],"method":[98,183],"leverages":[99],"Proximal":[101],"Policy":[102],"Optimization":[103],"(PPO)":[104],"strategy":[105],"assign":[107],"learnable":[108],"importance":[109],"scores":[110,127],"structural":[112],"units":[113],"like":[114],"filters":[115],"neurons":[117],"across":[118,177],"all":[119],"layers":[120],"trained":[123],"model.":[125],"These":[126],"get":[128],"sampled":[129],"from":[130,146],"Bernoulli":[132],"distribution":[133],"determine":[135],"decisions.":[138],"PPO":[140],"agents":[141],"learn":[142],"accuracy-aware":[144],"rewards":[145],"downstream":[148],"classification":[149],"task.":[150],"Additionally,":[151],"compression":[155,163,207,251],"slider":[156],"mechanism":[157],"enables":[159,239],"user-defined":[160],"control":[161,195,241],"over":[162,196,201,242],"rates,":[164],"ensuring":[165],"balanced":[166],"sparsity.":[167],"Experiments":[168],"benchmark":[170],"as":[173],"VGG16":[174,200],"AlexNet":[176],"two":[178],"datasets":[179],"demonstrate":[180],"our":[182,236],"achieves":[184],"better":[185],"trade-offs":[186],"between":[187],"model":[188,224],"compression,":[191],"while":[192,227],"offering":[193],"finer":[194],"granularity.":[198],"For":[199],"CIFAR-10,":[202],"achieve":[204],"total":[206],"85.14%":[209],"with":[210],"drop":[212,230],"2.08%":[214],"inference":[216],"accuracy.":[217,234],"Also,":[218],"AlexNet,":[220],"prune":[222],"by":[225],"77.67%,":[226],"observing":[228],"2.84%":[232],"Moreover,":[235],"approach":[238],"precise":[240],"process,":[245],"allowing":[246],"flexible":[248],"targeted":[250],"strategies":[252],"suitable":[253],"real-world":[255],"deployment.":[256]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-24T00:00:00"}