{"id":"https://openalex.org/W7084138116","doi":"https://doi.org/10.1145/3731569.3764806","title":"HedraRAG: Co-Optimizing Generation and Retrieval for Heterogeneous RAG Workflows","display_name":"HedraRAG: Co-Optimizing Generation and Retrieval for Heterogeneous RAG Workflows","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W7084138116","doi":"https://doi.org/10.1145/3731569.3764806"},"language":"en","primary_location":{"id":"doi:10.1145/3731569.3764806","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764806","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731569.3764806","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhengding Hu","orcid":"https://orcid.org/0009-0005-8500-6173"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengding Hu","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, La Jolla, California, USA"],"raw_orcid":"https://orcid.org/0009-0005-8500-6173","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vibha Murthy","orcid":"https://orcid.org/0009-0009-3288-6858"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vibha Murthy","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, La Jolla, California, USA"],"raw_orcid":"https://orcid.org/0009-0009-3288-6858","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zaifeng Pan","orcid":"https://orcid.org/0000-0002-6759-2616"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaifeng Pan","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, La Jolla, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-6759-2616","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanlu Li","orcid":"https://orcid.org/0000-0003-0098-0670"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wanlu Li","raw_affiliation_strings":["Nano and Chemical Engineering, University of California San Diego, La Jolla, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-0098-0670","affiliations":[{"raw_affiliation_string":"Nano and Chemical Engineering, University of California San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyi Fang","orcid":"https://orcid.org/0009-0008-0660-0003"},"institutions":[{"id":"https://openalex.org/I1330254920","display_name":"Hudson Institute","ror":"https://ror.org/014n3ck53","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1330254920"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyi Fang","raw_affiliation_strings":["RegAilator Inc, Hudson, Ohio, USA"],"raw_orcid":"https://orcid.org/0009-0008-0660-0003","affiliations":[{"raw_affiliation_string":"RegAilator Inc, Hudson, Ohio, USA","institution_ids":["https://openalex.org/I1330254920"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yufei Ding","orcid":"https://orcid.org/0000-0002-8716-5793"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["University of California San Diego, La Jolla, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-8716-5793","affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuke Wang","orcid":"https://orcid.org/0000-0003-1634-8549"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuke Wang","raw_affiliation_strings":["Computer Science, Rice University, Houston, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0003-1634-8549","affiliations":[{"raw_affiliation_string":"Computer Science, Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":1.0246,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82927855,"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":"623","last_page":"638"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10060","display_name":"Smoking Behavior and Cessation","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10060","display_name":"Smoking Behavior and Cessation","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10235","display_name":"Health disparities and outcomes","score":0.013899999670684338,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10027","display_name":"Diabetes, Cardiovascular Risks, and Lipoproteins","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8330000042915344},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6783000230789185},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.557200014591217},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5324000120162964},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4611999988555908},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4255000054836273}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8330000042915344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814300000667572},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6783000230789185},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6128000020980835},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C147358964","wikidata":"https://www.wikidata.org/wiki/Q1200992","display_name":"Abstraction layer","level":3,"score":0.27379998564720154}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731569.3764806","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764806","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731569.3764806","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764806","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8708120587","display_name":null,"funder_award_id":"2124039","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1988888548","https://openalex.org/W2912924812","https://openalex.org/W2998702515","https://openalex.org/W3048804154","https://openalex.org/W4388778348","https://openalex.org/W4393065402","https://openalex.org/W4406800520"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"identify":[4],"and":[5,19,44,60,73,93],"tackle":[6],"emerging":[7],"system-level":[8],"challenges":[9],"in":[10],"serving":[11],"heterogeneous":[12,106],"RAG":[13,107],"workflows,":[14],"characterized":[15],"by":[16],"complex":[17],"stages":[18],"diverse":[20],"request":[21],"patterns.":[22],"We":[23],"present":[24],"HedraRAG,":[25],"a":[26,32,81,102],"new":[27],"system":[28],"built":[29],"on":[30],"RAGraph,":[31],"graph-based":[33],"abstraction":[34],"that":[35,87,91],"exposes":[36],"optimization":[37],"opportunities":[38,48],"across":[39,70,80],"stage-level":[40],"parallelism,":[41],"intra-request":[42],"similarity,":[43],"inter-request":[45],"skewness.":[46],"These":[47],"are":[49,63],"expressed":[50],"through":[51],"graph":[52],"transformations,":[53],"including":[54],"node":[55],"splitting,":[56],"reordering,":[57],"edge":[58],"addition":[59],"rewiring.":[61],"Transformations":[62],"dynamically":[64],"applied":[65],"to":[66,95],"wavefronts":[67],"of":[68,84],"subgraphs":[69],"concurrent":[71],"requests":[72],"scheduled":[74],"onto":[75],"the":[76],"CPU-GPU":[77],"pipeline.":[78],"Experiments":[79],"wide":[82],"range":[83],"workflows":[85],"demonstrate":[86],"HedraRAG":[88],"achieves":[89],"more":[90],"1.5\u00d7":[92],"up":[94],"5\u00d7":[96],"speedup":[97],"over":[98],"existing":[99],"frameworks,":[100],"offering":[101],"comprehensive":[103],"solution":[104],"for":[105],"workload":[108],"serving.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
