DBScholar

Back to papers

Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment

Summary: Starling: a disk-resident, I/O-efficient HVSS framework for segment-wide vector search. Hybrid layout (in-memory navigation graph + reordered disk graph) and a block I/O strategy reduce disk traffic, enabling 33M 128-D vectors with >0.9 AP and ~1 ms latency, ~44x throughput vs prior methods. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
hed0af06d314156ab
Venue
SIGMOD
Year
2024
Pagerank
0.00010100279
Overall Rank
1,603 | 89.23%
DOI
10.1145/3639269

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{wang_sigmod24,
        title = {{Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment}},
        author = {Wang, Mengzhao and Xu, Weizhi and Yi, Xiaomeng and Wu, Songlin and Peng, Zhangyang and Ke, Xiangyu and Gao, Yunjun and Xu, Xiaoliang and Guo, Rentong and Xie, Charles},
        series = {{SIGMOD} '24},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3639269},
        url = {https://dl.acm.org/doi/10.1145/3639269},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 38 of 38 citing papers.

Rank Citing Paper Year Venue Pagerank
2,821 Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search 2025 SIGMOD 7.9674226e-05
4,051 Revisiting the Index Construction of Proximity Graph-Based Approximate Nearest Neighbor Search 2025 VLDB 6.8266649e-05
5,620 A Topology-Aware Localized Update Strategy for Graph-Based ANN Index 2026 VLDB 6.0596841e-05
6,244 Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search 2025 VLDB 5.8355024e-05
7,006 Accelerating Graph Indexing for ANNS on Modern CPUs 2025 SIGMOD 5.6212001e-05
7,318 An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models 2024 VLDB 5.5522339e-05
7,594 Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search 2026 SIGMOD 5.4865404e-05
7,811 PDX: A Data Layout for Vector Similarity Search 2025 SIGMOD 5.4476368e-05
8,350 Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal 2025 VLDB 5.3481387e-05
8,654 Turbocharging Vector Databases using Modern SSDs 2025 VLDB 5.2928388e-05
8,821 HAKES: Scalable Vector Database for Embedding Search Service 2025 VLDB 5.2697314e-05
9,064 Aster: Enhancing LSM-structures for Scalable Graph Database 2025 SIGMOD 5.2270607e-05
9,568 Distribution-Aware Exploration for Adaptive HNSW Search 2026 SIGMOD 5.154741e-05
9,912 DiskJoin: Large-scale Vector Similarity Join with SSD 2026 SIGMOD 5.1079647e-05
10,094 Select Edges Wisely: Monotonic Path Aware Graph Layout Optimization for Disk-based ANN Search 2025 VLDB 5.0783086e-05
10,168 GPS: Revisiting the Data Layout for Disk-based High-Dimensional Vector Search 2026 SIGMOD 5.0658661e-05
10,231 CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA 2026 SIGMOD 5.0547568e-05
10,330 Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search 2026 SIGMOD 5.0322912e-05
10,331 TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning 2026 SIGMOD 5.0322912e-05
10,333 Fast-Convergent Proximity Graphs for Approximate Nearest Neighbor Search 2026 SIGMOD 5.0322912e-05
10,407 Proximity Graphs for Similarity Search: Fast Construction, Lower Bounds, and Euclidean Separation 2026 PODS 4.9769913e-05
10,429 Balancing Global and Local: Representative Sampling for Large-Scale Vector Data 2026 SIGMOD 4.9769913e-05
10,455 Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search 2026 SIGMOD 4.9769913e-05
10,472 GEM: A Native Graph-based Index for Multi-Vector Retrieval 2026 SIGMOD 4.9769913e-05
10,520 TaCo: Data-adaptive and Query-aware Subspace Collision for High-dimensional Approximate Nearest Neighbor Search 2026 SIGMOD 4.9769913e-05
10,522 Through the Lens of Hubness: A Revisit on Graph-Based Approximate Nearest Neighbor Search: [Experiments & Analysis] 2026 SIGMOD 4.9769913e-05
10,546 SWIFT: Enabling Large-Scale Temporal Graph Learning on a Single Machine 2026 SIGMOD 4.9769913e-05
10,551 Accelerating High-Dimensional ANN Search via Skipping Redundant Distance Computations 2026 SIGMOD 4.9769913e-05
10,585 High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU 2026 SIGMOD 4.9769913e-05
10,646 Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph 2026 SIGMOD 4.9769913e-05
10,648 Efficient Vector Index Merging in Vector Databases 2026 SIGMOD 4.9769913e-05
10,688 RAIRS: Optimizing Redundant Assignment and List Layout for IVF-Based ANN Search 2026 SIGMOD 4.9769913e-05
10,736 I/O Optimizations for Graph-Based Disk-Resident Approximate Nearest Neighbor Search: A Design Space Exploration 2026 VLDB 4.9769913e-05
10,755 Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search 2026 VLDB 4.9769913e-05
10,830 Aker: Density-Aware Approximate Caching for Vector Search 2026 VLDB 4.9769913e-05
10,919 TEngineDB-V: An OLAP-Native Vector Search System for Large-k Workloads at Tencent 2026 VLDB 4.9769913e-05
11,037 Advances of Query Processing in Vector Databases 2026 VLDB 4.9769913e-05
11,057 Elastic Index Selection for Label-Hybrid AKNN Search 2026 VLDB 4.9769913e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 18 of 18 cited papers.

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

Rank Cited Paper Year Venue Pagerank
3 Pregel: A System for Large-Scale Graph Processing 2010 SIGMOD 0.0012087459
74 Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph 2019 VLDB 0.00037145866
189 Milvus: A Purpose-Built Vector Data Management System 2021 SIGMOD 0.0002585319
297 Query-Aware Locality-Sensitive Hashing for Approximate Nearest Neighbor Search 2016 VLDB 0.00021849337
339 AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data 2020 VLDB 0.00020561716
344 A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search 2021 VLDB 0.00020455839
712 Cache locality is not enough: High-Performance Nearest Neighbor Search with Product Quantization Fast Scan 2016 VLDB 0.00014593534
909 PASE: PostgreSQL Ultra-High-Dimensional Approximate Nearest Neighbor Search Extension 2020 SIGMOD 0.0001312576
1,325 VHP: Approximate Nearest Neighbor Search via Virtual Hypersphere Partitioning 2020 VLDB 0.00011016872
1,438 Speedup Graph Processing by Graph Ordering 2016 SIGMOD 0.00010647473
1,456 Manu: A Cloud Native Vector Database Management System 2022 VLDB 0.00010588868
1,681 HVS: Hierarchical Graph Structure Based on Voronoi Diagrams for Solving Approximate Nearest Neighbor Search 2022 VLDB 9.8836287e-05
1,894 iDEC: Indexable Distance Estimating Codes for Approximate Nearest Neighbor Search 2020 VLDB 9.4129766e-05
2,250 Streaming Graph Partitioning: An Experimental Study 2018 VLDB 8.7533947e-05
3,390 Experimental Analysis of Streaming Algorithms for Graph Partitioning 2019 SIGMOD 7.3484517e-05
4,987 LANNS: A Web-Scale Approximate Nearest Neighbor Lookup System 2022 VLDB 6.3237807e-05
7,260 An I/O-Efficient Disk-based Graph System for Scalable Second-Order Random Walk of Large Graphs 2022 VLDB 5.5695153e-05
7,323 LIDER: An Efficient High-dimensional Learned Index for Large-scale Dense Passage Retrieval 2023 VLDB 5.5516885e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 8,350 Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal 2025 VLDB
2 10,168 GPS: Revisiting the Data Layout for Disk-based High-Dimensional Vector Search 2026 SIGMOD
3 10,691 Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views: [Experiments & Analysis] 2026 SIGMOD
4 1,373 High-Throughput Vector Similarity Search in Knowledge Graphs 2023 SIGMOD
5 10,646 Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph 2026 SIGMOD
6 7,006 Accelerating Graph Indexing for ANNS on Modern CPUs 2025 SIGMOD
7 10,648 Efficient Vector Index Merging in Vector Databases 2026 SIGMOD
8 2,061 Similarity search in the blink of an eye with compressed indices 2023 VLDB
9 10,455 Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search 2026 SIGMOD
10 8,654 Turbocharging Vector Databases using Modern SSDs 2025 VLDB