High-Throughput Vector Similarity Search in Knowledge Graphs Article Swipe

PDF

Jason Mohoney , Anil Pacaci , Shihabur Rahman Chowdhury , Ali Mousavi , Ihab F. Ilyas , Umar Farooq Minhas , Jeffrey Pound , Theodoros Rekatsinas ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2304.01926

There is an increasing adoption of machine learning for encoding data into vectors to serve online recommendation and search use cases. As a result, recent data management systems propose augmenting query processing with online vector similarity search. In this work, we explore vector similarity search in the context of Knowledge Graphs (KGs). Motivated by the tasks of finding related KG queries and entities for past KG query workloads, we focus on hybrid vector similarity search (hybrid queries for short) where part of the query corresponds to vector similarity search and part of the query corresponds to predicates over relational attributes associated with the underlying data vectors. For example, given past KG queries for a song entity, we want to construct new queries for new song entities whose vector representations are close to the vector representation of the entity in the past KG query. But entities in a KG also have non-vector attributes such as a song associated with an artist, a genre, and a release date. Therefore, suggested entities must also satisfy query predicates over non-vector attributes beyond a vector-based similarity predicate. While these tasks are central to KGs, our contributions are generally applicable to hybrid queries. In contrast to prior works that optimize online queries, we focus on enabling efficient batch processing of past hybrid query workloads. We present our system, HQI, for high-throughput batch processing of hybrid queries. We introduce a workload-aware vector data partitioning scheme to tailor the vector index layout to the given workload and describe a multi-query optimization technique to reduce the overhead of vector similarity computations. We evaluate our methods on industrial workloads and demonstrate that HQI yields a 31x improvement in throughput for finding related KG queries compared to existing hybrid query processing approaches.

Related Topics

Computer Science

Data Mining

Artificial Intelligence

Concepts

Computer science Query expansion Web query classification Information retrieval Nearest neighbor search Similarity (geometry) Web search query Construct (python library) Sargable Vector space model Query language Focus (optics) Workload Query optimization Context (archaeology) Data mining Artificial intelligence Search engine Image (mathematics) Paleontology Operating system Physics Programming language Optics Biology

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2304.01926
PDF: https://arxiv.org/pdf/2304.01926
OA Status: green
Cited By: 3
Related Works: 10
OpenAlex ID: https://openalex.org/W4362656042

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4362656042

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2304.01926

Digital Object Identifier
Title: High-Throughput Vector Similarity Search in Knowledge Graphs

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2023

Year of publication
Publication date: 2023-04-04

Full publication date if available
Authors: Jason Mohoney, Anil Pacaci, Shihabur Rahman Chowdhury, Ali Mousavi, Ihab F. Ilyas, Umar Farooq Minhas, Jeffrey Pound, Theodoros Rekatsinas

List of authors in order
Landing page: https://arxiv.org/abs/2304.01926

Publisher landing page
PDF URL: https://arxiv.org/pdf/2304.01926

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2304.01926

Direct OA link when available
Concepts: Computer science, Query expansion, Web query classification, Information retrieval, Nearest neighbor search, Similarity (geometry), Web search query, Construct (python library), Sargable, Vector space model, Query language, Focus (optics), Workload, Query optimization, Context (archaeology), Data mining, Artificial intelligence, Search engine, Image (mathematics), Paleontology, Operating system, Physics, Programming language, Optics, Biology

Top concepts (fields/topics) attached by OpenAlex
Cited by: 3

Total citation count in OpenAlex
Citations by year (recent): 2025: 1, 2024: 2

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4362656042
doi	https://doi.org/10.48550/arxiv.2304.01926
ids.doi	https://doi.org/10.48550/arxiv.2304.01926
ids.openalex	https://openalex.org/W4362656042
fwci
type	preprint
title	High-Throughput Vector Similarity Search in Knowledge Graphs
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10627
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9965000152587891
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Advanced Image and Video Retrieval Techniques
topics[1].id	https://openalex.org/T11273
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9950000047683716
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Advanced Graph Neural Networks
topics[2].id	https://openalex.org/T11478
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9944999814033508
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1705
topics[2].subfield.display_name	Computer Networks and Communications
topics[2].display_name	Caching and Content Delivery
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.762695848941803
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C99016210
concepts[1].level	2
concepts[1].score	0.5743898749351501
concepts[1].wikidata	https://www.wikidata.org/wiki/Q5488129
concepts[1].display_name	Query expansion
concepts[2].id	https://openalex.org/C118689300
concepts[2].level	4
concepts[2].score	0.5573427677154541
concepts[2].wikidata	https://www.wikidata.org/wiki/Q7978614
concepts[2].display_name	Web query classification
concepts[3].id	https://openalex.org/C23123220
concepts[3].level	1
concepts[3].score	0.5500093102455139
concepts[3].wikidata	https://www.wikidata.org/wiki/Q816826
concepts[3].display_name	Information retrieval
concepts[4].id	https://openalex.org/C116738811
concepts[4].level	2
concepts[4].score	0.5351705551147461
concepts[4].wikidata	https://www.wikidata.org/wiki/Q608751
concepts[4].display_name	Nearest neighbor search
concepts[5].id	https://openalex.org/C103278499
concepts[5].level	3
concepts[5].score	0.5202432870864868
concepts[5].wikidata	https://www.wikidata.org/wiki/Q254465
concepts[5].display_name	Similarity (geometry)
concepts[6].id	https://openalex.org/C164120249
concepts[6].level	3
concepts[6].score	0.4944896697998047
concepts[6].wikidata	https://www.wikidata.org/wiki/Q995982
concepts[6].display_name	Web search query
concepts[7].id	https://openalex.org/C2780801425
concepts[7].level	2
concepts[7].score	0.4829903841018677
concepts[7].wikidata	https://www.wikidata.org/wiki/Q5164392
concepts[7].display_name	Construct (python library)
concepts[8].id	https://openalex.org/C192939062
concepts[8].level	4
concepts[8].score	0.4761086404323578
concepts[8].wikidata	https://www.wikidata.org/wiki/Q104840822
concepts[8].display_name	Sargable
concepts[9].id	https://openalex.org/C89686163
concepts[9].level	2
concepts[9].score	0.4650726318359375
concepts[9].wikidata	https://www.wikidata.org/wiki/Q1187982
concepts[9].display_name	Vector space model
concepts[10].id	https://openalex.org/C192028432
concepts[10].level	2
concepts[10].score	0.45723921060562134
concepts[10].wikidata	https://www.wikidata.org/wiki/Q845739
concepts[10].display_name	Query language
concepts[11].id	https://openalex.org/C192209626
concepts[11].level	2
concepts[11].score	0.45640575885772705
concepts[11].wikidata	https://www.wikidata.org/wiki/Q190909
concepts[11].display_name	Focus (optics)
concepts[12].id	https://openalex.org/C2778476105
concepts[12].level	2
concepts[12].score	0.4508677124977112
concepts[12].wikidata	https://www.wikidata.org/wiki/Q628539
concepts[12].display_name	Workload
concepts[13].id	https://openalex.org/C157692150
concepts[13].level	2
concepts[13].score	0.42400434613227844
concepts[13].wikidata	https://www.wikidata.org/wiki/Q2919848
concepts[13].display_name	Query optimization
concepts[14].id	https://openalex.org/C2779343474
concepts[14].level	2
concepts[14].score	0.4172241687774658
concepts[14].wikidata	https://www.wikidata.org/wiki/Q3109175
concepts[14].display_name	Context (archaeology)
concepts[15].id	https://openalex.org/C124101348
concepts[15].level	1
concepts[15].score	0.37366175651550293
concepts[15].wikidata	https://www.wikidata.org/wiki/Q172491
concepts[15].display_name	Data mining
concepts[16].id	https://openalex.org/C154945302
concepts[16].level	1
concepts[16].score	0.25368115305900574
concepts[16].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[16].display_name	Artificial intelligence
concepts[17].id	https://openalex.org/C97854310
concepts[17].level	2
concepts[17].score	0.23147252202033997
concepts[17].wikidata	https://www.wikidata.org/wiki/Q19541
concepts[17].display_name	Search engine
concepts[18].id	https://openalex.org/C115961682
concepts[18].level	2
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[18].display_name	Image (mathematics)
concepts[19].id	https://openalex.org/C151730666
concepts[19].level	1
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q7205
concepts[19].display_name	Paleontology
concepts[20].id	https://openalex.org/C111919701
concepts[20].level	1
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q9135
concepts[20].display_name	Operating system
concepts[21].id	https://openalex.org/C121332964
concepts[21].level	0
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q413
concepts[21].display_name	Physics
concepts[22].id	https://openalex.org/C199360897
concepts[22].level	1
concepts[22].score	0.0
concepts[22].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[22].display_name	Programming language
concepts[23].id	https://openalex.org/C120665830
concepts[23].level	1
concepts[23].score	0.0
concepts[23].wikidata	https://www.wikidata.org/wiki/Q14620
concepts[23].display_name	Optics
concepts[24].id	https://openalex.org/C86803240
concepts[24].level	0
concepts[24].score	0.0
concepts[24].wikidata	https://www.wikidata.org/wiki/Q420
concepts[24].display_name	Biology
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.762695848941803
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/query-expansion
keywords[1].score	0.5743898749351501
keywords[1].display_name	Query expansion
keywords[2].id	https://openalex.org/keywords/web-query-classification
keywords[2].score	0.5573427677154541
keywords[2].display_name	Web query classification
keywords[3].id	https://openalex.org/keywords/information-retrieval
keywords[3].score	0.5500093102455139
keywords[3].display_name	Information retrieval
keywords[4].id	https://openalex.org/keywords/nearest-neighbor-search
keywords[4].score	0.5351705551147461
keywords[4].display_name	Nearest neighbor search
keywords[5].id	https://openalex.org/keywords/similarity
keywords[5].score	0.5202432870864868
keywords[5].display_name	Similarity (geometry)
keywords[6].id	https://openalex.org/keywords/web-search-query
keywords[6].score	0.4944896697998047
keywords[6].display_name	Web search query
keywords[7].id	https://openalex.org/keywords/construct
keywords[7].score	0.4829903841018677
keywords[7].display_name	Construct (python library)
keywords[8].id	https://openalex.org/keywords/sargable
keywords[8].score	0.4761086404323578
keywords[8].display_name	Sargable
keywords[9].id	https://openalex.org/keywords/vector-space-model
keywords[9].score	0.4650726318359375
keywords[9].display_name	Vector space model
keywords[10].id	https://openalex.org/keywords/query-language
keywords[10].score	0.45723921060562134
keywords[10].display_name	Query language
keywords[11].id	https://openalex.org/keywords/focus
keywords[11].score	0.45640575885772705
keywords[11].display_name	Focus (optics)
keywords[12].id	https://openalex.org/keywords/workload
keywords[12].score	0.4508677124977112
keywords[12].display_name	Workload
keywords[13].id	https://openalex.org/keywords/query-optimization
keywords[13].score	0.42400434613227844
keywords[13].display_name	Query optimization
keywords[14].id	https://openalex.org/keywords/context
keywords[14].score	0.4172241687774658
keywords[14].display_name	Context (archaeology)
keywords[15].id	https://openalex.org/keywords/data-mining
keywords[15].score	0.37366175651550293
keywords[15].display_name	Data mining
keywords[16].id	https://openalex.org/keywords/artificial-intelligence
keywords[16].score	0.25368115305900574
keywords[16].display_name	Artificial intelligence
keywords[17].id	https://openalex.org/keywords/search-engine
keywords[17].score	0.23147252202033997
keywords[17].display_name	Search engine
language	en
locations[0].id	pmh:oai:arXiv.org:2304.01926
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2304.01926
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2304.01926
locations[1].id	doi:10.48550/arxiv.2304.01926
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2304.01926
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5041665675
authorships[0].author.orcid	https://orcid.org/0000-0001-5497-0481
authorships[0].author.display_name	Jason Mohoney
authorships[0].author_position	first
authorships[0].raw_author_name	Mohoney, Jason
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5052360032
authorships[1].author.orcid	https://orcid.org/0000-0003-4994-8014
authorships[1].author.display_name	Anil Pacaci
authorships[1].author_position	middle
authorships[1].raw_author_name	Pacaci, Anil
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5055538536
authorships[2].author.orcid	https://orcid.org/0000-0002-6232-2027
authorships[2].author.display_name	Shihabur Rahman Chowdhury
authorships[2].author_position	middle
authorships[2].raw_author_name	Chowdhury, Shihabur Rahman
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5119011707
authorships[3].author.orcid	https://orcid.org/0000-0002-4084-6102
authorships[3].author.display_name	Ali Mousavi
authorships[3].author_position	middle
authorships[3].raw_author_name	Mousavi, Ali
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5000141065
authorships[4].author.orcid	https://orcid.org/0000-0001-9052-9714
authorships[4].author.display_name	Ihab F. Ilyas
authorships[4].author_position	middle
authorships[4].raw_author_name	Ilyas, Ihab F.
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5032253873
authorships[5].author.orcid	https://orcid.org/0009-0005-6520-3794
authorships[5].author.display_name	Umar Farooq Minhas
authorships[5].author_position	middle
authorships[5].raw_author_name	Minhas, Umar Farooq
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5060727577
authorships[6].author.orcid	https://orcid.org/0000-0001-6281-6345
authorships[6].author.display_name	Jeffrey Pound
authorships[6].author_position	middle
authorships[6].raw_author_name	Pound, Jeffrey
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5002060759
authorships[7].author.orcid	https://orcid.org/0000-0001-6148-1854
authorships[7].author.display_name	Theodoros Rekatsinas
authorships[7].author_position	last
authorships[7].raw_author_name	Rekatsinas, Theodoros
authorships[7].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2304.01926
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	High-Throughput Vector Similarity Search in Knowledge Graphs
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10627
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9965000152587891
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Advanced Image and Video Retrieval Techniques
related_works	https://openalex.org/W2096359267, https://openalex.org/W2901901036, https://openalex.org/W2006459955, https://openalex.org/W2013069866, https://openalex.org/W2026738364, https://openalex.org/W1793997780, https://openalex.org/W2538384344, https://openalex.org/W2124814993, https://openalex.org/W2093300859, https://openalex.org/W2146885082
cited_by_count	3
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	2
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2304.01926
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2304.01926
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2304.01926
primary_location.id	pmh:oai:arXiv.org:2304.01926
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2304.01926
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2304.01926
publication_date	2023-04-04
publication_year	2023
referenced_works_count	0
abstract_inverted_index.a	22, 113, 146, 154, 160, 163, 178, 232, 250, 274
abstract_inverted_index.As	21
abstract_inverted_index.In	37, 197
abstract_inverted_index.KG	59, 65, 110, 141, 147, 282
abstract_inverted_index.We	218, 230, 262
abstract_inverted_index.an	2, 158
abstract_inverted_index.as	153
abstract_inverted_index.by	53
abstract_inverted_index.in	45, 138, 145, 277
abstract_inverted_index.is	1
abstract_inverted_index.of	5, 48, 56, 81, 91, 135, 213, 227, 258
abstract_inverted_index.on	70, 208, 266
abstract_inverted_index.to	13, 85, 95, 118, 131, 187, 194, 199, 238, 244, 254, 285
abstract_inverted_index.we	40, 68, 116, 206
abstract_inverted_index.31x	275
abstract_inverted_index.But	143
abstract_inverted_index.For	106
abstract_inverted_index.HQI	272
abstract_inverted_index.and	17, 61, 89, 162, 248, 269
abstract_inverted_index.are	129, 185, 191
abstract_inverted_index.for	8, 63, 77, 112, 122, 223, 279
abstract_inverted_index.new	120, 123
abstract_inverted_index.our	189, 220, 264
abstract_inverted_index.the	46, 54, 82, 92, 102, 132, 136, 139, 240, 245, 256
abstract_inverted_index.use	19
abstract_inverted_index.HQI,	222
abstract_inverted_index.KGs,	188
abstract_inverted_index.also	148, 170
abstract_inverted_index.data	10, 25, 104, 235
abstract_inverted_index.have	149
abstract_inverted_index.into	11
abstract_inverted_index.must	169
abstract_inverted_index.over	97, 174
abstract_inverted_index.part	80, 90
abstract_inverted_index.past	64, 109, 140, 214
abstract_inverted_index.song	114, 124, 155
abstract_inverted_index.such	152
abstract_inverted_index.that	202, 271
abstract_inverted_index.this	38
abstract_inverted_index.want	117
abstract_inverted_index.with	32, 101, 157
abstract_inverted_index.There	0
abstract_inverted_index.While	182
abstract_inverted_index.batch	211, 225
abstract_inverted_index.close	130
abstract_inverted_index.date.	165
abstract_inverted_index.focus	69, 207
abstract_inverted_index.given	108, 246
abstract_inverted_index.index	242
abstract_inverted_index.prior	200
abstract_inverted_index.query	30, 66, 83, 93, 172, 216, 288
abstract_inverted_index.serve	14
abstract_inverted_index.tasks	55, 184
abstract_inverted_index.these	183
abstract_inverted_index.where	79
abstract_inverted_index.whose	126
abstract_inverted_index.work,	39
abstract_inverted_index.works	201
abstract_inverted_index.(KGs).	51
abstract_inverted_index.Graphs	50
abstract_inverted_index.beyond	177
abstract_inverted_index.cases.	20
abstract_inverted_index.entity	137
abstract_inverted_index.genre,	161
abstract_inverted_index.hybrid	71, 195, 215, 228, 287
abstract_inverted_index.layout	243
abstract_inverted_index.online	15, 33, 204
abstract_inverted_index.query.	142
abstract_inverted_index.recent	24
abstract_inverted_index.reduce	255
abstract_inverted_index.scheme	237
abstract_inverted_index.search	18, 44, 74, 88
abstract_inverted_index.short)	78
abstract_inverted_index.tailor	239
abstract_inverted_index.vector	34, 42, 72, 86, 127, 133, 234, 241, 259
abstract_inverted_index.yields	273
abstract_inverted_index.(hybrid	75
abstract_inverted_index.artist,	159
abstract_inverted_index.central	186
abstract_inverted_index.context	47
abstract_inverted_index.entity,	115
abstract_inverted_index.explore	41
abstract_inverted_index.finding	57, 280
abstract_inverted_index.machine	6
abstract_inverted_index.methods	265
abstract_inverted_index.present	219
abstract_inverted_index.propose	28
abstract_inverted_index.queries	60, 76, 111, 121, 283
abstract_inverted_index.related	58, 281
abstract_inverted_index.release	164
abstract_inverted_index.result,	23
abstract_inverted_index.satisfy	171
abstract_inverted_index.search.	36
abstract_inverted_index.system,	221
abstract_inverted_index.systems	27
abstract_inverted_index.vectors	12
abstract_inverted_index.adoption	4
abstract_inverted_index.compared	284
abstract_inverted_index.contrast	198
abstract_inverted_index.describe	249
abstract_inverted_index.enabling	209
abstract_inverted_index.encoding	9
abstract_inverted_index.entities	62, 125, 144, 168
abstract_inverted_index.evaluate	263
abstract_inverted_index.example,	107
abstract_inverted_index.existing	286
abstract_inverted_index.learning	7
abstract_inverted_index.optimize	203
abstract_inverted_index.overhead	257
abstract_inverted_index.queries,	205
abstract_inverted_index.queries.	196, 229
abstract_inverted_index.vectors.	105
abstract_inverted_index.workload	247
abstract_inverted_index.Knowledge	49
abstract_inverted_index.Motivated	52
abstract_inverted_index.construct	119
abstract_inverted_index.efficient	210
abstract_inverted_index.generally	192
abstract_inverted_index.introduce	231
abstract_inverted_index.suggested	167
abstract_inverted_index.technique	253
abstract_inverted_index.workloads	268
abstract_inverted_index.Therefore,	166
abstract_inverted_index.applicable	193
abstract_inverted_index.associated	100, 156
abstract_inverted_index.attributes	99, 151, 176
abstract_inverted_index.augmenting	29
abstract_inverted_index.increasing	3
abstract_inverted_index.industrial	267
abstract_inverted_index.management	26
abstract_inverted_index.non-vector	150, 175
abstract_inverted_index.predicate.	181
abstract_inverted_index.predicates	96, 173
abstract_inverted_index.processing	31, 212, 226, 289
abstract_inverted_index.relational	98
abstract_inverted_index.similarity	35, 43, 73, 87, 180, 260
abstract_inverted_index.throughput	278
abstract_inverted_index.underlying	103
abstract_inverted_index.workloads,	67
abstract_inverted_index.workloads.	217
abstract_inverted_index.approaches.	290
abstract_inverted_index.corresponds	84, 94
abstract_inverted_index.demonstrate	270
abstract_inverted_index.improvement	276
abstract_inverted_index.multi-query	251
abstract_inverted_index.optimization	252
abstract_inverted_index.partitioning	236
abstract_inverted_index.vector-based	179
abstract_inverted_index.computations.	261
abstract_inverted_index.contributions	190
abstract_inverted_index.recommendation	16
abstract_inverted_index.representation	134
abstract_inverted_index.workload-aware	233
abstract_inverted_index.high-throughput	224
abstract_inverted_index.representations	128
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	8
citation_normalized_percentile