{"id":"https://openalex.org/W7108957961","doi":"https://doi.org/10.1145/3769778","title":"DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention","display_name":"DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W7108957961","doi":"https://doi.org/10.1145/3769778"},"language":"en","primary_location":{"id":"doi:10.1145/3769778","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769778","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-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":null,"display_name":"Hao Yuan","orcid":"https://orcid.org/0009-0002-6502-7696"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Yuan","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Ai","orcid":"https://orcid.org/0009-0006-0746-8222"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Ai","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiange Wang","orcid":"https://orcid.org/0000-0002-4847-6070"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiange Wang","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peizheng Li","orcid":"https://orcid.org/0009-0007-0047-2576"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peizheng Li","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiayang Yu","orcid":"https://orcid.org/0009-0003-6651-5787"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayang Yu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaoyi Chen","orcid":"https://orcid.org/0009-0008-5518-9978"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyi Chen","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinbo Yang","orcid":"https://orcid.org/0009-0004-3756-9273"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Yang","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanfeng Zhang","orcid":"https://orcid.org/0000-0002-9871-0304"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Zhang","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenbo Fu","orcid":"https://orcid.org/0009-0009-2317-9561"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenbo Fu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yingyou Wen","orcid":"https://orcid.org/0000-0002-6659-1785"},"institutions":[{"id":"https://openalex.org/I4210134419","display_name":"Neusoft (China)","ror":"https://ror.org/02zc84r97","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingyou Wen","raw_affiliation_strings":["Neusoft AI Magic Technology Research, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Neusoft AI Magic Technology Research, Shenyang, China","institution_ids":["https://openalex.org/I4210134419"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78392374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"6","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.22120000422000885,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.22120000422000885,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.20000000298023224,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.12729999423027039,"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/cache","display_name":"Cache","score":0.7146999835968018},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6324999928474426},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6136999726295471},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5175999999046326},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.48539999127388},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4226999878883362},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.42160001397132874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607000112533569},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7146999835968018},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5004000067710876},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.42160001397132874},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C51185590","wikidata":"https://www.wikidata.org/wiki/Q1017228","display_name":"Bus sniffing","level":5,"score":0.3000999987125397},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2915000021457672}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769778","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769778","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6280721782","display_name":null,"funder_award_id":"62461146205, U2241212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2761338514","https://openalex.org/W2963339397","https://openalex.org/W4210798430","https://openalex.org/W4281725510","https://openalex.org/W4387321091","https://openalex.org/W4388979610","https://openalex.org/W4396601684","https://openalex.org/W4408061109","https://openalex.org/W4411374335","https://openalex.org/W4412944812"],"related_works":[],"abstract_inverted_index":{"Graph-based":[0],"Retrieval-Augmented":[1],"Generation":[2],"(GraphRAG)":[3],"has":[4],"emerged":[5],"as":[6,30],"a":[7,60,111,128,150],"promising":[8],"paradigm":[9],"for":[10,117],"enhancing":[11],"LLM":[12,177],"reliability":[13],"by":[14,180,186],"enabling":[15,142],"multi-hop":[16],"reasoning":[17],"over":[18],"graph-structured":[19,28],"knowledge.":[20],"However,":[21],"existing":[22],"LLMs":[23],"struggle":[24],"to":[25,47,69,161,188],"efficiently":[26],"process":[27],"inputs,":[29],"traditional":[31],"attention":[32,63,67,88],"mechanisms":[33],"are":[34],"sequence-based":[35],"and":[36,50,93,148,157,171,182],"introduce":[37,57],"significant":[38],"redundancy":[39],"when":[40],"serializing":[41],"graphs":[42],"into":[43],"prompt":[44,140],"sequences,":[45],"leading":[46],"excessive":[48],"computation":[49,68],"memory":[51],"overhead.":[52,103],"To":[53],"address":[54],"this,":[55],"we":[56,108],"dependency":[58,87,118],"attention,":[59],"novel":[61],"graph-aware":[62],"mechanism":[64],"that":[65,82,134,154,174],"restricts":[66],"token":[70,91],"pairs":[71,92],"with":[72],"structural":[73],"dependencies":[74],"in":[75,146],"the":[76],"retrieved":[77],"subgraph.":[78],"Unlike":[79],"standard":[80],"self-attention":[81],"computes":[83],"fully":[84],"connected":[85],"interactions,":[86],"prunes":[89],"irrelevant":[90],"reuses":[94],"computations":[95],"along":[96],"shared":[97],"relational":[98],"paths,":[99],"substantially":[100],"reducing":[101],"inference":[102,178],"Building":[104],"on":[105],"this":[106],"idea,":[107],"develop":[109],"DepCache,":[110],"KV":[112,123,130,136,163],"cache":[113,124,131,164],"management":[114],"framework":[115],"tailored":[116],"attention.":[119],"DepCache":[120,175],"enables":[121],"efficient":[122,143],"reuse":[125,132,145],"through":[126],"(i)":[127],"graph-based":[129],"strategy":[133],"aligns":[135],"caches":[137],"across":[138,168],"varying":[139],"contexts,":[141],"cross-request":[144],"GraphRAG,":[147],"(ii)":[149],"locality-aware":[151],"replacement":[152],"policy":[153],"leverages":[155],"spatial":[156],"temporal":[158],"access":[159],"patterns":[160],"improve":[162],"hit":[165],"rate.":[166],"Evaluations":[167],"diverse":[169],"models":[170],"datasets":[172],"show":[173],"improves":[176],"throughput":[179],"1.5\u00d7-5.0\u00d7":[181],"reduces":[183],"time-to-first-token":[184],"latency":[185],"up":[187],"3.2\u00d7,":[189],"without":[190],"compromising":[191],"generation":[192],"accuracy.":[193]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-06T00:00:00"}