Page 118 - 《软件学报》2026年第3期

邱海浪 等: LSMDiskANN: 更新友好型磁盘向量索引框架 1081

3467101]
[3] Zhu J. Application of vector search in batch retrieval of e-commerce products. Bao-steel Technology, 2023(4): 13–16 (in Chinese with
English abstract). [doi: 10.3969/j.issn.1008-0716.2023.04.004]
[4] Indyk P, Motwani R. Approximate nearest neighbors: Towards removing the curse of dimensionality. In: Proc. of the 13th Annual ACM
Symp. on Theory of Computing. Dallas: ACM, 1998. 604–613. [doi: 10.1145/276698.276876]
[5] Malkov YA, Yashunin DA. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs.
IEEE Trans. on Pattern Analysis and Machine Intelligence, 2020, 42(4): 824–836. [doi: 10.1109/TPAMI.2018.2889473]
[6] Ono N, Matsui Y. Relative NN-descent: A fast index construction for graph-based approximate nearest neighbor search. In: Proc. of the
31st ACM Int’l Conf. on Multimedia. Ottawa: ACM, 2023. 1659–1667. [doi: 10.1145/1963405.1963487]
[7] Dong W, Moses C, Li K. Efficient k-nearest neighbor graph construction for generic similarity measures. In: Proc. of the 20th Int’l Conf.
on World Wide Web. Hyderabad: ACM, 2011. 577–586. [doi: 10.1145/1963405.1963487]
[8] Harwood B, Drummond T. FANNG: Fast approximate nearest neighbour graphs. In: Proc. of the 2016 IEEE Conf. on Computer Vision
and Pattern Recognition. Las Vegas: IEEE, 2016. 5713–5722. [doi: 10.1109/CVPR.2016.616]
[9] Jégou H, Douze M, Schmid C. Product quantization for nearest neighbor search. IEEE Trans. on Pattern Analysis and Machine
Intelligence, 2011, 33(1): 117–128. [doi: 10.1109/TPAMI.2010.57]
[10] Datar M, Immorlica N, Indyk P, Mirrokni VS. Locality-sensitive hashing scheme based on p-stable distributions. In: Proc. of the 20th
Annual Symp. on Computational Geometry. Brooklyn: ACM, 2004. 253–262. [doi: 10.1145/997817.997857]
[11] Chen Q, Zhao B, Wang HD, Li MQ, Liu CJ, Li ZZ, Yang M, Wang JD. SPANN: Highly-efficient billion-scale approximate nearest
neighbor search. In: Proc. of the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 398.
[12] Dasgupta S, Freund Y. Random projection trees and low dimensional manifolds. In: Proc. of the 40th Annual ACM Symp. on Theory of
Computing. Victoria: ACM, 2008. 537–546. [doi: 10.1145/1374376.1374452]
[13] Jayaram Subramanya S, Devvrit, Kadekodi R, Krishaswamy R, Simhadri HV. DiskANN: Fast accurate billion-point nearest neighbor
search on a single node. In: Proc. of the 33rd Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc.,
2019. 1233.
[14] Ren J, Zhang MJ, Li D. HM-ANN: Efficient billion-point nearest neighbor search on heterogeneous memory. In: Proc. of the 34th Int’l
Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2020. 895.
[15] Abu-El-Haija S, Kothari N, Lee J, Natsev P, Toderici G, Varadarajan B, Vijayanarasimhan S. YouTube-8M: A large-scale video
classification benchmark. arXiv:1609.08675, 2016.
[16] Priem J, Piwowar H, Orr R. OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts.
arXiv:2205.01833, 2022.
[17] Xu YM, Liang HY, Li J, Xu ST, Chen Q, Zhang QX, Li C, Yang ZY, Yang F, Yang YQ, Cheng P, Yang M. SPFresh: Incremental in-
place update for billion-scale vector search. In: Proc. of the 29th Symp. on Operating Systems Principles. Koblenz: ACM, 2023. 545–561.
[doi: 10.1145/3600006.3613166]
[18] Singh A, Subramanya SJ, Krishnaswamy R, Simhadri HV. FreshDiskANN: A fast and accurate graph-based ANN index for streaming
similarity search. arXiv:2105.09613, 2021.
[19] Mohoney J, Pacaci A, Chowdhury SR, Minhas UF, Pound J, Renggli C, Reyhani N, Ilyas IF, Rekatsinas T, Venkataraman S. Incremental
IVF index maintenance for streaming vector search. arXiv:2411.00970, 2024.
[20] Wei CX, Wu B, Wang S, Lou RJ, Zhan CQ, Li FF, Cai YZ. AnalyticDB-V: A hybrid analytical engine towards query fusion for
structured and unstructured data. Proc. of the VLDB Endowment, 2020, 13(12): 3152–3165. [doi: 10.14778/3415478.3415541]
[21] Wang JG, Yi XM, Guo RT, Jin H, Xu P, Li SJ, Wang XY, Guo XZ, Li CM, Xu XH, Yu K, Yuan YX, Zou YH, Long JQ, Cai YD, Li ZX,
Zhang ZF, Mo YH, Gu J, Jiang RY, Wei Y, Xie C. Milvus: A purpose-built vector data management system. In: Proc. of the 2021 Int’l
Conf. on Management of Data. ACM, 2021. 2614–2627. [doi: 10.1145/3448016.3457550]
[22] Qdrant. High-performance vector search at scale. 2025. https://qdrant.tech/
[23] Weaviate. For AI engineers who think big. 2025. https://weaviate.io/
[24] Vardhan Simhadri H, Aumüller M, Ingber A, Douze M, Williams G, Dobson Manohar M, Baranchuk D, Liberty E, Liu F, Landrum B,
Karjikar M, Dhulipala L, Chen M, Chen Y, Ma R, Zhang K, Cai YZ, Shi JY, Chen YZ, Zheng WG, Wan ZH, Yin J, Huang B. Results of
the big ANN: NeurIPS’23 competition. arXiv:2409.17424, 2024.
[25] Yu S, Lin SY, Gong SF, Xie YQ, Liu RC, Zhou YJ, Sun J, Zhang YF, Li GL, Yu G. A topology-aware localized update strategy for
graph-based ANN index. arXiv:2503.00402, 2025.
[26] Wang MZ, Xu WZ, Yi XM, Wu SL, Peng ZY, Ke XY, Gao YJ, Xu XL, Guo RT, Xie C. Starling: An I/O-efficient disk-resident graph