{"id":"https://openalex.org/W4311224386","doi":"https://doi.org/10.1109/igsc55832.2022.9969374","title":"MOSP: Multi-Objective Sensitivity Pruning of Deep Neural Networks","display_name":"MOSP: Multi-Objective Sensitivity Pruning of Deep Neural Networks","publication_year":2022,"publication_date":"2022-10-24","ids":{"openalex":"https://openalex.org/W4311224386","doi":"https://doi.org/10.1109/igsc55832.2022.9969374"},"language":"en","primary_location":{"id":"doi:10.1109/igsc55832.2022.9969374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igsc55832.2022.9969374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 13th International Green and Sustainable Computing Conference (IGSC)","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/A5101507575","display_name":"Muhammad Sabih","orcid":"https://orcid.org/0000-0003-2066-646X"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Muhammad Sabih","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Department of Computer Science,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Department of Computer Science,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051197396","display_name":"Ashutosh Mishra","orcid":"https://orcid.org/0000-0001-8579-5583"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ashutosh Mishra","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072039340","display_name":"Frank Hannig","orcid":"https://orcid.org/0000-0003-3663-6484"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Hannig","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Department of Computer Science,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Department of Computer Science,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076672029","display_name":"J\u00fcrgen Teich","orcid":"https://orcid.org/0000-0001-6285-5862"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jurgen Teich","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Department of Computer Science,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Department of Computer Science,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9138,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75639273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/computer-science","display_name":"Computer science","score":0.8274590969085693},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6493460536003113},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.579626739025116},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5387206673622131},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.529392659664154},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5189375877380371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5142809748649597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4568418562412262},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.41797661781311035},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.13048622012138367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274590969085693},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6493460536003113},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.579626739025116},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5387206673622131},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.529392659664154},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5189375877380371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142809748649597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4568418562412262},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.41797661781311035},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.13048622012138367},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/igsc55832.2022.9969374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igsc55832.2022.9969374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 13th International Green and Sustainable Computing Conference (IGSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/446014","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/446014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W176909285","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W2101234009","https://openalex.org/W2194775991","https://openalex.org/W2294543795","https://openalex.org/W2407146636","https://openalex.org/W2594633041","https://openalex.org/W2604319603","https://openalex.org/W2605409611","https://openalex.org/W2805003733","https://openalex.org/W2805390961","https://openalex.org/W2808168148","https://openalex.org/W2808938483","https://openalex.org/W2885311373","https://openalex.org/W2885369545","https://openalex.org/W2895260923","https://openalex.org/W2911964244","https://openalex.org/W2915589364","https://openalex.org/W2939504873","https://openalex.org/W2962861284","https://openalex.org/W2962965870","https://openalex.org/W2963809228","https://openalex.org/W2963918968","https://openalex.org/W2965862774","https://openalex.org/W2967733054","https://openalex.org/W2980137827","https://openalex.org/W3007623470","https://openalex.org/W3034251466","https://openalex.org/W3034290785","https://openalex.org/W3034819536","https://openalex.org/W3085380432","https://openalex.org/W3099365437","https://openalex.org/W3109212549","https://openalex.org/W3118608800","https://openalex.org/W3212328129","https://openalex.org/W4220818878","https://openalex.org/W4287686688","https://openalex.org/W4287756710","https://openalex.org/W4288356321","https://openalex.org/W4295312788","https://openalex.org/W6600609147","https://openalex.org/W6637373629","https://openalex.org/W6675354045","https://openalex.org/W6677103964","https://openalex.org/W6726275242","https://openalex.org/W6734194636","https://openalex.org/W6736518430","https://openalex.org/W6751739117","https://openalex.org/W6751979845","https://openalex.org/W6753278433","https://openalex.org/W6759263581","https://openalex.org/W6762703681","https://openalex.org/W6766978945","https://openalex.org/W6781934123","https://openalex.org/W6783213970","https://openalex.org/W6891886391"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4382323155","https://openalex.org/W4280563792","https://openalex.org/W4315697128","https://openalex.org/W4318719684","https://openalex.org/W4318559728","https://openalex.org/W3183136280","https://openalex.org/W2775233965","https://openalex.org/W3092292339","https://openalex.org/W3100944160"],"abstract_inverted_index":{"Deep":[0],"neural":[1,28,215],"networks":[2,216],"(DNNs)":[3],"are":[4],"computationally":[5],"intensive,":[6],"making":[7],"them":[8],"difficult":[9],"to":[10,68,159,170,173,183,198],"deploy":[11],"on":[12,73,105],"resource-constrained":[13],"embedded":[14],"systems.":[15],"Model":[16],"compression":[17,37],"is":[18,111,226],"a":[19,27,90,114,137,144,152],"set":[20],"of":[21,118,134,136,162],"techniques":[22],"that":[23],"removes":[24],"redundancies":[25],"from":[26],"network":[29],"with":[30,53,113,228],"affordable":[31],"degradation":[32,188],"in":[33,187,189,219],"task":[34,190],"performance.":[35],"Most":[36],"methods":[38,50],"do":[39],"not":[40],"target":[41,119,141],"hardware-based":[42],"objectives":[43,120,142],"such":[44,121],"as":[45,122,143],"latency":[46,52,77,223],"directly;":[47],"however,":[48],"few":[49],"approximate":[51],"floating-point":[54],"operations":[55,59],"(FLOPs)":[56],"or":[57,116],"multiply-accumulate":[58],"(MACs).":[60],"Using":[61],"these":[62],"indirect":[63],"metrics":[64],"cannot":[65],"directly":[66],"translate":[67],"the":[69,74,132,140,196,204,209],"relevant":[70],"performance":[71,191],"metric":[72],"hardware,":[75],"i.e.,":[76],"and":[78,102,126,217,222,225],"throughput.":[79],"To":[80],"address":[81],"this":[82],"limitation,":[83],"we":[84,150,165],"introduce":[85],"Multi-Objective":[86],"Sensitivity":[87],"Pruning,":[88],"\u201cMOSP,\u201d":[89],"three-stage":[91],"pipeline":[92,110,177],"for":[93],"filter":[94,168],"pruning:":[95],"hardware-aware":[96],"sensitivity":[97,133],"analysis,":[98],"Criteria-optimal":[99,153],"configuration":[100,154],"selection,":[101],"pruning":[103,181],"based":[104],"explainable":[106],"AI":[107],"(XAI).":[108],"Our":[109,128,206],"compatible":[112],"single":[115],"combination":[117],"latency,":[123],"energy":[124],"consumption,":[125],"accuracy.":[127],"method":[129,207,212],"first":[130],"formulates":[131],"layers":[135],"model":[138],"against":[139],"classical":[145],"machine":[146],"learning":[147],"problem.":[148],"Next,":[149],"choose":[151],"controlled":[155],"by":[156],"hyperparameters":[157],"specific":[158],"each":[160],"objective":[161,201],"choice.":[163],"Finally,":[164],"apply":[166],"XAI-based":[167],"ranking":[169],"select":[171],"filters":[172],"be":[174],"pruned.":[175],"The":[176],"follows":[178],"an":[179],"iterative":[180],"methodology":[182],"recover":[184],"any":[185],"loss":[186],"(e.g.,":[192],"accuracy).":[193],"We":[194],"allow":[195],"user":[197],"prefer":[199],"one":[200],"function":[202],"over":[203],"other.":[205],"outperforms":[208],"selected":[210],"baseline":[211],"across":[213],"different":[214],"datasets":[218],"both":[220],"accuracy":[221],"reductions":[224],"competitive":[227],"state-of-the-art":[229],"approaches.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}