Page 140 - 《软件学报》2026年第3期

王可 等: 面向批量更新的向量索引召回率优化 1103

[32] 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]
[33] Durante Z, Huang QY, Wake N, Gong R, Park JS, Sarkar B, Taori R, Noda Y, Terzopoulos D, Choi Y, Ikeuchi K, Vo H, Fei-Fei L, Gao
JF. Agent AI: Surveying the horizons of multimodal interaction. arXiv:2401.03568, 2024.
[34] Subramanya SJ, 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.
[35] 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.
[36] Gollapudi S, Karia N, Sivashankar V, Krishnaswamy R, Begwani N, Raz S, Lin YY, Zhang Y, Mahapatro N, Srinivasan P, Singh A,
Simhadri HV. Filtered-DiskANN: Graph algorithms for approximate nearest neighbor search with filters. In: Proc. of the 2023 ACM Web
Conf. Austin: ACM, 2023. 3406–3416. [doi: 10.1145/3543507.3583552]
[37] GitHub, Inc. SPTAG. 2025. https://github.com/microsoft/SPTAG
[38] Iwasaki M, Miyazaki D. Optimization of indexing based on k-nearest neighbor graph for proximity search in high-dimensional data.
arXiv:1810.07355, 2018.
[39] Elliott OP, Clark J. The impacts of data, ordering, and intrinsic dimensionality on recall in hierarchical navigable small worlds. In: Proc.
of the 2024 ACM SIGIR Int’l Conf. on Theory of Information Retrieval. Washington: ACM, 2024. 25–33. [doi: 10.1145/3664190.
3672512]
[40] Li CL, Zhang MJ, Andersen DG, He YX. Improving approximate nearest neighbor search through learned adaptive early termination. In:
Proc. of the 2020 ACM SIGMOD Int’l Conf. on Management of Data. Portland: ACM, 2020. 2539–2554. [doi: 10.1145/3318464.
3380600]
[41] Jégou H, Douze M, Schmid C. Searching with quantization: Approximate nearest neighbor search using short codes and distance
estimators. Technical Report, RR-7020, INRIA, 2009. [doi: 10.1023/A:1011139631724]
[42] INRIA. Datasets for approximate nearest neighbor search. 2011. http://corpus-texmex.irisa.fr/
[43] Million Song dataset benchmarks. 2012. http://www.ifs.tuwien.ac.at/mir/msd/
[44] Russell S, Christopher M, Jeffrey P. Enron email dataset. 2015. https://www.cs.cmu.edu/~./enron/

附中文参考文献
[7] 王永胜, 李培峰, 王中卿, 朱巧明. 多模态信息抽取研究综述. 软件学报, 2025, 36(4): 1665–1691. http://www.jos.org.cn/1000-9825/
7245.htm [doi: 10.13328/j.cnki.jos.007245]
[13] 朱炫鹏, 姚海东, 刘隽, 熊先奎. 大语言模型算法演进综述. 中兴通讯技术, 2024, 30(2): 9–20. [doi: 10.12142/ZTETJ.202402003]
[18] 刘泽垣, 王鹏江, 宋晓斌, 张欣, 江奔奔. 大语言模型的幻觉问题研究综述. 软件学报, 2025, 36(3): 1152–1185. http://www.jos.org.cn/1000-
9825/7242.htm [doi: 10.13328/j.cnki.jos.007242]

作者简介
王可, 博士生, CCF 学生会员, 主要研究领域为数据库系统, 向量数据库.
胡思劼, 硕士生, 主要研究领域为数据库系统, 向量索引.
胡卉芪, 博士, 教授, 博士生导师, CCF 专业会员, 主要研究领域为数据库, 分布式系统.
赵明昊, 博士, 助理教授, 博士生导师, CCF 专业会员, 主要研究领域为云计算/存储, 操作系统, 软件工程.
魏星, 博士, CCF 专业会员, 主要研究领域为向量数据库, 异构数据库, 机器学习.
屠要峰, 博士, 研究员, CCF 杰出会员, 主要研究领域为数据库, 大数据, 机器学习.
周烜, 博士, 教授, 博士生导师, CCF 专业会员, 主要研究领域为数据管理系统.