HAKES: Scalable Vector Database for Embedding Search Service

Summary: HAKES introduces a two-stage ANN index combining compressed-vector filtering, learned tuning, and adaptive early termination for high-recall search under concurrent updates. Its disaggregated distributed design decouples learned-parameter management and delivers up to 16× higher throughput than prior systems. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: h1bf5a488e99adceb
Venue: VLDB
Year: 2025
Pagerank: 5.0807138e-05
Overall Rank: 10,089 | 32.17%
DOI: 10.14778/3746405.3746427

Incoming Non-self Citations Over Time

Authors

1. Guoyu Hu (National University of Singapore)
2. Shaofeng Cai (National University of Singapore)
3. Tien Tuan Anh Dinh (Deakin University)
4. Zhongle Xie (Zhejiang University)
5. Cong Yue (National University of Singapore)
6. Gang Chen (Zhejiang University)
7. Beng Chin Ooi (National University of Singapore; Zhejiang University)

BibTeX Citation

@article{hu_vldb25,
        title = {{HAKES: Scalable Vector Database for Embedding Search Service}},
        author = {Hu, Guoyu and Cai, Shaofeng and Dinh, Tien Tuan Anh and Xie, Zhongle and Yue, Cong and Chen, Gang and Ooi, Beng Chin},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {9},
        pages = {3049--3062},
        doi = {10.14778/3746405.3746427},
        url = {https://doi.org/10.14778/3746405.3746427},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,163	GPS: Revisiting the Data Layout for Disk-based High-Dimensional Vector Search	2026	SIGMOD	5.0682654e-05
10,457	FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances	2026	SIGMOD	4.9793485e-05
10,697	SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search	2026	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 14 of 14 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
74	Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph	2019	VLDB	0.00037091678
194	Milvus: A Purpose-Built Vector Data Management System	2021	SIGMOD	0.00025636725
341	AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data	2020	VLDB	0.00020539791
713	Cache locality is not enough: High-Performance Nearest Neighbor Search with Product Quantization Fast Scan	2016	VLDB	0.00014571977
804	RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search	2024	SIGMOD	0.00013832333
839	Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination	2020	SIGMOD	0.00013547412
1,462	Manu: A Cloud Native Vector Database Management System	2022	VLDB	0.0001058099
1,601	High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations	2023	SIGMOD	0.00010103316
1,613	Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment	2024	SIGMOD	0.00010072237
1,625	Towards Efficient Index Construction and Approximate Nearest Neighbor Search in High-Dimensional Spaces	2023	VLDB	0.0001004502
2,060	Similarity search in the blink of an eye with compressed indices	2023	VLDB	9.0983169e-05
2,265	ELPIS: Graph-Based Similarity Search for Scalable Data Science	2023	VLDB	8.7238222e-05
2,969	Locality-Sensitive Hashing Scheme based on Longest Circular Co-Substring	2020	SIGMOD	7.8000797e-05
5,007	LANNS: A Web-Scale Approximate Nearest Neighbor Lookup System	2022	VLDB	6.3169238e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	7,564	SIEVE: Effective Filtered Vector Search with Collection of Indexes	2025	VLDB
2	7,004	Accelerating Graph Indexing for ANNS on Modern CPUs	2025	SIGMOD
3	7,432	Cracking Vector Search Indexes	2025	VLDB
4	10,078	Accelerating Approximate Nearest Neighbor Search in Hierarchical Graphs: Efficient Level Navigation with Shortcuts	2025	VLDB
5	10,648	HIRE: A Hybrid Learned Index for Robust and Efficient Performance under Mixed Workloads	2026	SIGMOD
6	10,443	Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search	2026	SIGMOD
7	10,637	Efficient Vector Index Merging in Vector Databases	2026	SIGMOD
8	10,836	HEXA: A Disjoint-Subgraph-Based Indexing Framework for Approximate Nearest Neighbor Search at Billion Scale	2026	VLDB
9	9,955	Turbocharging Vector Databases using Modern SSDs	2025	VLDB
10	8,946	HAP: An Efficient Hamming Space Index Based on Augmented Pigeonhole Principle	2022	SIGMOD