{"id":"https://openalex.org/W4408048984","doi":"https://doi.org/10.1109/bigcom65357.2024.00013","title":"Towards Efficient Inference on Mobile Device via Pruning","display_name":"Towards Efficient Inference on Mobile Device via Pruning","publication_year":2024,"publication_date":"2024-08-09","ids":{"openalex":"https://openalex.org/W4408048984","doi":"https://doi.org/10.1109/bigcom65357.2024.00013"},"language":"en","primary_location":{"id":"doi:10.1109/bigcom65357.2024.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcom65357.2024.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Big Data Computing and Communications (BigCom)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100462285","display_name":"Zhiyuan Wang","orcid":"https://orcid.org/0000-0002-1966-2421"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Wang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101202459","display_name":"Haisheng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haisheng Tan","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.3147,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86603269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.885699987411499,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.885699987411499,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220926284790039},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6785397529602051},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6354150772094727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4582899808883667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3277195692062378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220926284790039},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6785397529602051},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6354150772094727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4582899808883667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3277195692062378},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigcom65357.2024.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcom65357.2024.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Big Data Computing and Communications (BigCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2112016429","https://openalex.org/W2799197246","https://openalex.org/W2903711666","https://openalex.org/W2962851801","https://openalex.org/W2963122961","https://openalex.org/W2982479999","https://openalex.org/W3097304224","https://openalex.org/W6638632666","https://openalex.org/W6639703010","https://openalex.org/W6677580257","https://openalex.org/W6696004547","https://openalex.org/W6700264148","https://openalex.org/W6720242923","https://openalex.org/W6726275242","https://openalex.org/W6734062232","https://openalex.org/W6738642365","https://openalex.org/W6744700018","https://openalex.org/W6746331415","https://openalex.org/W6751349269","https://openalex.org/W6755166560","https://openalex.org/W6767423016","https://openalex.org/W6770860620","https://openalex.org/W6778883912","https://openalex.org/W6788811087"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Mobile":[0],"edge":[1],"intelligence":[2],"requires":[3],"deploying":[4],"deep":[5,110],"learning":[6,111],"neural":[7,278],"network":[8,279],"models":[9,112,280],"on":[10,47,91,113,123,134,218,236,255,273],"mobile":[11,48,62,78,114,283,314],"devices.":[12,49,115,180,315],"Model":[13],"sparsity":[14,40,75],"techniques,":[15],"including":[16],"low-precision":[17,98],"quantization":[18,99,169,196],"and":[19,100,198,281],"pruning,":[20],"have":[21,130,159],"been":[22],"proposed":[23],"to":[24,51,146,171,259,290,311],"achieve":[25],"higher":[26],"model":[27,35,58,138],"compression":[28],"rates":[29],"at":[30],"a":[31,131],"lower":[32],"cost":[33],"of":[34,54,74,109,118,177,240,302],"accuracy":[36,223],"degradation.":[37],"However,":[38],"these":[39,85],"techniques":[41,76],"still":[42],"face":[43],"challenges":[44],"in":[45,61,77,285],"deployment":[46,73,108],"Due":[50],"the":[52,93,124,174,182,185,190,200,206,219,226,237,244,252,261,286,298],"lack":[53],"capability":[55],"for":[56,103,194,222],"fine-tuning":[57],"weight":[59],"parameters":[60],"inference":[63,79,94,104,135,152,162,186,300],"frameworks,":[64],"any":[65],"pruning":[66,101,149,215,234,248],"technique":[67],"must":[68],"be":[69,308],"carefully":[70],"applied.":[71],"The":[72,116],"frameworks":[80],"is":[81,121],"challenging.":[82],"To":[83,154],"address":[84],"challenges,":[86],"we":[87,158],"propose":[88],"PoI":[89],"(Pruning":[90],"Inference),":[92],"framework,":[95],"which":[96],"integrates":[97],"optimization":[102,203],"computation,":[105],"enabling":[106],"efficient":[107,148],"design":[117],"this":[119,156,247],"framework":[120],"based":[122,217,272],"observation":[125],"that":[126],"memory":[127,256],"access":[128,257],"patterns":[129,258],"crucial":[132],"impact":[133,254],"latency":[136,301],"during":[137,151],"execution.":[139,153],"This":[140],"provides":[141],"us":[142],"with":[143],"an":[144,161,213],"opportunity":[145],"perform":[147],"operations":[150,235],"realize":[155],"idea,":[157],"designed":[160],"computation":[163,229],"framework.":[164],"Firstly,":[165],"it":[166,188,210,232],"supports":[167],"different":[168,178],"bit-widths":[170,197],"fully":[172],"exploit":[173],"computational":[175],"capabilities":[176],"hardware":[179],"After":[181],"user":[183],"specifies":[184],"model,":[187],"checks":[189],"current":[191,291],"device's":[192],"support":[193],"various":[195],"sets":[199],"corresponding":[201,238],"compilation":[202],"options.":[204],"During":[205],"actual":[207],"execution":[208,230],"process,":[209,231],"can":[211,296,307],"select":[212],"appropriate":[214],"ratio":[216,239],"user-specified":[220],"tolerance":[221],"loss.":[224],"In":[225],"specific":[227],"operator":[228],"performs":[233],"intra-kernel":[241],"computations.":[242],"At":[243],"same":[245],"time,":[246],"takes":[249],"into":[250],"account":[251],"potential":[253],"minimize":[260],"additional":[262],"overhead":[263],"caused":[264],"by":[265],"cache":[266],"misses.":[267],"We":[268],"evaluated":[269],"our":[270,294,305],"implementation":[271,295,306],"commonly":[274],"used":[275],"computer":[276],"vision":[277],"popular":[282,313],"devices":[284],"real":[287],"world.":[288],"Compared":[289],"mainstream":[292],"solutions,":[293],"reduce":[297],"average":[299],"models.":[303],"Moreover,":[304],"easily":[309],"migrated":[310],"other":[312]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}