{"id":"https://openalex.org/W4417403126","doi":"https://doi.org/10.1109/pact65351.2025.00037","title":"Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations","display_name":"Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4417403126","doi":"https://doi.org/10.1109/pact65351.2025.00037"},"language":null,"primary_location":{"id":"doi:10.1109/pact65351.2025.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact65351.2025.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th International Conference on Parallel Architectures and Compilation Techniques (PACT)","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/A5101073011","display_name":"Yujeong Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yujeong Choi","raw_affiliation_strings":["KAIST,School of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698124","display_name":"John Kim","orcid":"https://orcid.org/0000-0003-3958-3891"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"John Kim","raw_affiliation_strings":["KAIST,School of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091648103","display_name":"Minsoo Rhu","orcid":"https://orcid.org/0000-0003-3303-8681"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsoo Rhu","raw_affiliation_strings":["KAIST,School of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101073011"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5214075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.3630000054836273,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.3630000054836273,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.14890000224113464,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.08110000193119049,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/inference","display_name":"Inference","score":0.666100025177002},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6330000162124634},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.48089998960494995},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4156999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224999904632568},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.666100025177002},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6330000162124634},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2777480716","wikidata":"https://www.wikidata.org/wiki/Q23582796","display_name":"Resource consumption","level":2,"score":0.27219998836517334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pact65351.2025.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact65351.2025.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th International Conference on Parallel Architectures and Compilation Techniques (PACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315121","display_name":"Samsung Advanced Institute of Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1539971231","https://openalex.org/W2061574886","https://openalex.org/W2102709380","https://openalex.org/W2103010325","https://openalex.org/W2156077332","https://openalex.org/W2475334473","https://openalex.org/W2605350416","https://openalex.org/W2723293840","https://openalex.org/W2794670651","https://openalex.org/W2914554687","https://openalex.org/W2926143647","https://openalex.org/W2947737663","https://openalex.org/W2962745591","https://openalex.org/W2979719709","https://openalex.org/W2984020950","https://openalex.org/W3016842236","https://openalex.org/W3016939927","https://openalex.org/W3017091196","https://openalex.org/W3017148238","https://openalex.org/W3042495273","https://openalex.org/W3043023836","https://openalex.org/W3043433718","https://openalex.org/W3101026687","https://openalex.org/W3113181213","https://openalex.org/W3131607724","https://openalex.org/W3155243801","https://openalex.org/W3158702178","https://openalex.org/W3158783012","https://openalex.org/W3160344148","https://openalex.org/W3169109617","https://openalex.org/W3206393216"],"related_works":[],"abstract_inverted_index":{"While":[0],"providing":[1,79],"low":[2],"latency":[3],"is":[4,16,27],"a":[5,69],"fundamental":[6],"requirement":[7,61],"in":[8,19,93,100],"deploying":[9],"recommendation":[10,64,108],"services,":[11],"achieving":[12,84],"high":[13,85],"resource":[14,77],"utility":[15],"also":[17],"crucial":[18],"cost-effectively":[20],"maintaining":[21],"the":[22,39,58,106],"datacenter.":[23],"Co-locating":[24],"model":[25],"workers":[26,44],"an":[28,89],"effective":[29,94],"way":[30],"to":[31,66],"maximize":[32],"query-level":[33],"parallelism":[34],"and":[35,75],"server":[36,50],"throughput,":[37],"but":[38],"interference":[40],"caused":[41],"by":[42],"concurrent":[43],"at":[45],"shared":[46],"resources":[47],"can":[48],"prevent":[49],"queries":[51],"from":[52],"meeting":[53],"its":[54,76],"SLA.":[55],"Hera":[56,87],"utilizes":[57],"heterogeneous":[59],"memory":[60],"of":[62,72],"multi-tenant":[63],"models":[65,74],"intelligently":[67],"determine":[68],"productive":[70],"set":[71],"colocated":[73],"allocation,":[78],"fast":[80],"response":[81],"time":[82],"while":[83],"throughput.":[86],"achieves":[88],"average":[90],"37.3%":[91],"improvement":[92],"machine":[95],"utilization,":[96],"enabling":[97],"26%":[98],"reduction":[99],"required":[101],"servers,":[102],"significantly":[103],"improving":[104],"upon":[105],"baseline":[107],"inference":[109],"server.":[110]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-16T00:00:00"}