The project is a collection of recent research in areas such as ANN(Approximate Nearest Neighbor) and Vector Database, including research reports, academic papers and datasets etc.
We also hold regular paper readings together, so feel free to share your ideas.
该项目收集了ANN(近似近邻搜索)和向量数据库等领域的最新研究,包括研究报告、学术论文和数据集等。
我们还会定期举办论文共读活动,欢迎共同交流.
Contributions are always welcome! Make an individual pull request for each suggestion.
- 1. Survey
- 2. System
- 3. Graph based Index
- 4. Quantization based Index
- 5. Hash based Index
- 6. Tree based Index
- 7. Disk based Index
- 8. Hybrid Queries
[1] Approximate Nearest Neighbor Search on High Dimensional Data — Experiments, Analyses, and Improvement TKDE 2020. paper
Wen Li, Ying Zhang , Yifang Sun, Wei Wang, Mingjie Li , Wenjie Zhang , Xuemin Lin
[2] New trends in high-D vector similarity search: al-driven, progressive, and distributed VLDB 2021. paper slid
Karima Echihabi, Kostas Zoumpatianos, Themis Palpanas
[1] ANNA: Specialized Architecture for Approximate Nearest Neighbor Search HPCA 2022. paper
Yejin Lee, Hyunji Choi, Sunhong Min and so on
[2] HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory NIPS 2020. paper
Jie Ren, Minjia Zhang, Dong Li
[3] SONG: Approximate Nearest Neighbor Search on GPU ICDE 2020. paper
Weijie Zhao, Shulong Tan, Ping Li
[1] Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchial Navigable Small World Graphs paper
Yu A. Malkov, D. A. Yashunin
[2] Approximate nearest neighbor algorithm based on navigable small world graphs Information Systems 2014. paper
Yury Malkov, Alexander Ponomarenko, Andrey Logvinov, Vladimir Krylov
[3] A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search VLDB 2022. paper
Mengzhao Wang, Xiaoliang Xu, Qiang Yue, Yuxiang Wang
[4] Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph VLDB 2019. paper
Cong Fu, Chao Xiang, Changxu Wang, Deng Cai
[1] Product Quantization for Nearest Neighbor Search TPAMI 2019. paper
Herve J ´ egou, Matthijs Douze, Cordelia Schmid
[2] Optimized Product Quantization TPAMI 2013. paper
Tiezheng Ge, Kaiming He, Qifa Ke, Jian Sun
[3] The Inverted Multi-Index TPAMI 2014. paper
Artem Babenko, Victor Lempitsky
[4] Additive Quantization for Extreme Vector Compression CVPR 2014. paper
Artem Babenko, Victor Lempitsky
[5]Accelerating Large-Scale Inference with Anisotropic Vector Quantization ICML 2020. paper
Ruiqi Guo, Philip Sun, Erik Lindgren
[1] Similarity Search in High Dimensions via Hashing VLDB 1999. paper
Aristides Gionis, Piotr Indyk, Rajeev Motwani
[2] SRS: solving c -approximate nearest neighbor queries in high dimensional euclidean space with a tiny index VLDB 2014. paper
Yifang Sun, Wei Wang, Jianbin Qin, Ying Zhang, Xuemin Lin
[3] Locality-Sensitive Hashing Scheme Based on p-Stable Distributions SCG 2004.paper
Mayur Datar, Nicole Immorlica, Piotr Indyk, Vahab S. Mirrokni
[4] Query-aware locality-sensitive hashing for approximate nearest neighbor search VLDB 2015. paper
Qiang Huang, Jianlin Feng, Yikai Zhang
[1] Data Structures and Algorithms for Nearest Neighbor Search in General Metric Spaces SODA 1993. paper
Peter N. Yianilos
[2] Fast Nearest Neighbor Retrieval for Bregman Divergences ICML 2008. paper
Lawrence Cayton
[1] DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node NIPS 2019. paper
Suhas Jayaram Subramanya, Devvrit, Rohan Kadekodi, Ravishankar Krishaswamy, Harsha Vardhan Simhadri
[1] HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints CIKM '22. paper
Wei Wu, Junlin He, Yu Qiao, Guoheng Fu, Li Liu, Jin Yu
姓名 | 介绍 | 简介 | 联系 |
---|---|---|---|
苏鹏 | Datawhale 成员,东北大学硕士 | https://github.com/SuperSupeng | wechat: subranium |
王梦召 | 浙江大学博士 | ||
张鹏程 | 上海交通大学博士 | https://github.com/pzque | zhangpc123@outlook.com |
王泽宇 | 复旦大学博士 | ||
田冰 | 华中科技大学博士 | https://github.com/tianbing111 | tbing@hust.edu.cn |