{"id":"https://openalex.org/W7164808342","doi":"https://doi.org/10.1145/3805622.3810580","title":"MCHRAG: Multi-Centroid Hierarchical Indexing for Efficient Incremental RAG","display_name":"MCHRAG: Multi-Centroid Hierarchical Indexing for Efficient Incremental RAG","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164808342","doi":"https://doi.org/10.1145/3805622.3810580"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810580","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810580","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810580","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138682900","display_name":"Yuan Ren","orcid":"https://orcid.org/0009-0003-6954-9691"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Ren","raw_affiliation_strings":["Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6954-9691","affiliations":[{"raw_affiliation_string":"Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016458854","display_name":"Mingxue Liao","orcid":"https://orcid.org/0000-0001-6928-6885"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxue Liao","raw_affiliation_strings":["Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6928-6885","affiliations":[{"raw_affiliation_string":"Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065151055","display_name":"Gang Zhou","orcid":"https://orcid.org/0009-0002-1180-6942"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Zhou","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1180-6942","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138683811","display_name":"Jinxing Peng","orcid":"https://orcid.org/0009-0001-0637-4068"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxing Peng","raw_affiliation_strings":["Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0637-4068","affiliations":[{"raw_affiliation_string":"Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138633010","display_name":"Pin Lv","orcid":"https://orcid.org/0009-0006-4754-4445"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pin Lv","raw_affiliation_strings":["Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-4754-4445","affiliations":[{"raw_affiliation_string":"Institute of Automation\uff0cChinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96161695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.49410000443458557,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.49410000443458557,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.12200000137090683,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.0551999993622303,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.6822999715805054},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.541100025177002},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4742000102996826},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44620001316070557},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42879998683929443},{"id":"https://openalex.org/keywords/routing-table","display_name":"Routing table","score":0.4235000014305115},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4221999943256378},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4205000102519989},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4075999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465000152587891},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6822999715805054},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C184896649","wikidata":"https://www.wikidata.org/wiki/Q290066","display_name":"Routing table","level":4,"score":0.4235000014305115},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810580","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810580","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810580","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810580","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2012833704","https://openalex.org/W2147717514","https://openalex.org/W2889787757","https://openalex.org/W2963469388","https://openalex.org/W2998702515","https://openalex.org/W3099700870","https://openalex.org/W3115947671","https://openalex.org/W3190126809","https://openalex.org/W4382053179","https://openalex.org/W4389984066","https://openalex.org/W4402670856","https://openalex.org/W4402684046","https://openalex.org/W4404534210","https://openalex.org/W4405283668","https://openalex.org/W4412944752","https://openalex.org/W4415797504","https://openalex.org/W7160193996"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"over":[3],"dynamically":[4],"growing":[5],"long-text":[6],"corpora":[7],"demands":[8],"indexing":[9,32,138,144],"mechanisms":[10],"that":[11,165],"are":[12],"both":[13],"efficient":[14],"and":[15,19,33,39,104,139,145,153,160,181],"update-friendly.":[16],"Prior":[17],"graph-":[18],"hierarchy-augmented":[20],"RAG":[21],"systems":[22],"often":[23],"rely":[24],"on":[25,52,158],"LLM-based":[26],"summarization":[27],"or":[28,168],"entity\u2013relation":[29],"extraction":[30],"during":[31],"maintenance,":[34,140],"incurring":[35],"high":[36,133],"construction":[37,152],"latency":[38],"substantial":[40],"token":[41,147],"cost.":[42],"We":[43],"propose":[44],"MCHRAG,":[45],"a":[46,53,75,93,114],"hierarchical":[47],"semantic":[48],"routing":[49,77,111],"framework":[50],"based":[51],"Multi-Centroid":[54],"Routing":[55],"Tree":[56],"designed":[57],"for":[58],"streaming":[59],"updates.":[60],"MCHRAG":[61,141,166],"first":[62],"partitions":[63],"embeddings":[64],"into":[65],"coarse":[66],"hash":[67],"buckets":[68],"via":[69],"hyperplane":[70],"locality-sensitive":[71],"hashing,":[72],"then":[73],"builds":[74],"coarse-to-fine":[76],"hierarchy":[78],"in":[79],"the":[80,108],"embedding":[81],"space,":[82],"where":[83],"each":[84],"tree":[85],"node":[86],"(including":[87],"leaf":[88,118],"buckets)":[89],"is":[90],"represented":[91],"by":[92,121],"small":[94,115],"set":[95,116],"of":[96,117],"vector":[97],"prototypes":[98],"with":[99,132,177],"radius":[100],"constraints.":[101],"Both":[102],"retrieval":[103,170],"incremental":[105],"insertion":[106],"follow":[107],"same":[109],"top-down":[110],"to":[112],"select":[113],"buckets,":[119],"followed":[120],"exact":[122],"similarity":[123],"reranking":[124],"within":[125],"routed":[126],"candidates,":[127],"enabling":[128],"bounded":[129],"candidate":[130],"size":[131],"recall.":[134],"By":[135],"eliminating":[136],"LLM-dependent":[137],"achieves":[142],"zero":[143],"update":[146,154,182],"consumption":[148],"while":[149],"substantially":[150],"reducing":[151],"latency.":[155],"Extensive":[156],"experiments":[157],"long-context":[159],"multi-document":[161],"QA":[162],"benchmarks":[163],"show":[164],"matches":[167],"improves":[169],"quality,":[171],"especially":[172],"recall":[173],"under":[174],"distractor-heavy":[175],"settings,":[176],"significantly":[178],"lower":[179],"build":[180],"costs.":[183]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}