{"id":"https://openalex.org/W4390188870","doi":"https://doi.org/10.1109/hpec58863.2023.10363610","title":"PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models","display_name":"PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4390188870","doi":"https://doi.org/10.1109/hpec58863.2023.10363610"},"language":"en","primary_location":{"id":"doi:10.1109/hpec58863.2023.10363610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.13441","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103040030","display_name":"Neelesh Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"Southern California University for Professional Studies","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neelesh Gupta","raw_affiliation_strings":["University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073951710","display_name":"Pengmiao Zhang","orcid":"https://orcid.org/0000-0002-5411-3305"},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"Southern California University for Professional Studies","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengmiao Zhang","raw_affiliation_strings":["University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042560222","display_name":"Rajgopal Kannan","orcid":"https://orcid.org/0000-0001-8736-3012"},"institutions":[{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajgopal Kannan","raw_affiliation_strings":["DEVCOM Army Research Lab"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Lab","institution_ids":["https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033166029","display_name":"Viktor K. Prasanna","orcid":"https://orcid.org/0000-0002-1609-8589"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"Southern California University for Professional Studies","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Prasanna","raw_affiliation_strings":["University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103040030"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"],"apc_list":null,"apc_paid":null,"fwci":0.4739,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66364372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9936000108718872,"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":0.9936000108718872,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9926000237464905,"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"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8155683279037476},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5949139595031738},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5317800045013428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5173572897911072},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5161636471748352},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5152469277381897},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46118077635765076},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45500800013542175},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4204801619052887},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3448871970176697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155683279037476},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5949139595031738},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5317800045013428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5173572897911072},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5161636471748352},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5152469277381897},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46118077635765076},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45500800013542175},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4204801619052887},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448871970176697},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec58863.2023.10363610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.13441","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13441","pdf_url":"https://arxiv.org/pdf/2402.13441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.13441","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13441","pdf_url":"https://arxiv.org/pdf/2402.13441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5458957665","display_name":null,"funder_award_id":"CCF-1919289","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6092014333","display_name":"SPX: Collaborative Research: FASTLEAP: FPGA based compact Deep Learning Platform","funder_award_id":"1919289","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390188870.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W107619411","https://openalex.org/W109781734","https://openalex.org/W635149649","https://openalex.org/W1506806321","https://openalex.org/W1821462560","https://openalex.org/W1962768644","https://openalex.org/W1977556410","https://openalex.org/W2053076698","https://openalex.org/W2064675550","https://openalex.org/W2128462109","https://openalex.org/W2171006257","https://openalex.org/W2194775991","https://openalex.org/W2540580618","https://openalex.org/W2560647685","https://openalex.org/W2734941459","https://openalex.org/W2762076598","https://openalex.org/W2988190042","https://openalex.org/W3011374900","https://openalex.org/W3042879175","https://openalex.org/W3177079991","https://openalex.org/W4200409985","https://openalex.org/W4212774754","https://openalex.org/W4229010634","https://openalex.org/W4229042463","https://openalex.org/W4244939384","https://openalex.org/W4292169167","https://openalex.org/W4308090461","https://openalex.org/W6638523607","https://openalex.org/W6665271869","https://openalex.org/W6744527873","https://openalex.org/W6749259350","https://openalex.org/W6793787867","https://openalex.org/W6795140394","https://openalex.org/W6810964969"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W2055243143","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3035501883"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"proven":[5],"to":[6,47,74,152,163,205,220],"be":[7],"effective":[8],"models":[9,30,77,103,166,177,207,222],"for":[10,58,104,108,146],"accurate":[11],"Memory":[12],"Access":[13],"Prediction":[14],"(MAP),":[15],"a":[16,69,113,179,192],"critical":[17],"task":[18],"in":[19,60,150,156],"mitigating":[20],"memory":[21,90,105],"latency":[22],"through":[23],"data":[24],"prefetching.":[25],"However,":[26],"existing":[27],"DNN-based":[28],"MAP":[29,76],"suffer":[31],"from":[32,122],"the":[33,80,120,123,164],"challenges":[34],"such":[35],"as":[36,137],"significant":[37],"physical":[38],"storage":[39],"space":[40],"and":[41,111,134,142,170,213],"poor":[42],"inference":[43],"latency,":[44],"primarily":[45],"due":[46],"their":[48,154],"large":[49,100],"number":[50],"of":[51,173,189,227],"parameters.":[52],"These":[53],"limitations":[54],"render":[55],"them":[56],"impractical":[57],"deployment":[59],"real-world":[61],"scenarios.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"propose":[67],"PaCKD,":[68],"Pattern-Clustered":[70],"Knowledge":[71],"Distillation":[72],"approach":[73,85,130,197],"compress":[75],"while":[78,185],"maintaining":[79,186],"prediction":[81,107],"performance.":[82],"The":[83],"PaCKD":[84],"encompasses":[86],"three":[87],"steps:":[88],"clustering":[89],"access":[91,106],"sequences":[92],"into":[93],"distinct":[94],"partitions":[95],"involving":[96],"similar":[97],"patterns,":[98],"training":[99,112],"pattern-specific":[101,125],"teacher":[102,165],"each":[109],"partition,":[110],"single":[114],"lightweight":[115],"student":[116,176,206,221],"model":[117,182],"by":[118],"distilling":[119],"knowledge":[121,211,228],"trained":[124,208,223],"teachers.":[126],"We":[127],"evaluate":[128],"our":[129,175],"on":[131],"LSTM,":[132],"MLP-Mixer,":[133],"ResNet":[135],"models,":[136],"they":[138],"exhibit":[139],"diverse":[140],"structures":[141],"are":[143],"widely":[144,158],"used":[145,159],"image":[147],"classification":[148],"tasks":[149],"order":[151],"test":[153],"effectiveness":[155],"four":[157],"graph":[160],"applications.":[161],"Compared":[162],"with":[167,209],"5.406M":[168],"parameters":[169],"an":[171,187,199,214],"F1-score":[172],"0.4626,":[174],"achieve":[178],"552":[180],"x":[181],"size":[183],"compression":[184],"Fl-score":[188],"0.4538":[190],"(with":[191],"1.92%":[193],"performance":[194],"drop).":[195],"Our":[196],"yields":[198],"8.70":[200],"%":[201,216],"higher":[202,217],"result":[203,218],"compared":[204,219],"standard":[210],"distillation":[212],"8.88":[215],"without":[224],"any":[225],"form":[226],"distillation.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2023-12-26T00:00:00"}