awesome-vector-ANN-search-papers

A list of papers in the field of approximate nearest neighbor search on high-dimensional vectors.

We refine papers according to categories and research groups. Other reading reference and notes for ANN study is coming soon.

Let's dive into ANN search and vector database!

Introduction of ANN search

In general, there are many great articles in the website of Pinecone and Zilliz, including core components, deep dives, user cases and ML foundations in the field of vector databases.

If you are a Chinese developer and want to learn about the getting-started concepts and techniques in ANN search with vector datasets, here is a blog that contains most of the concepts for a beginner.

Papers Refined with Categories

In this section, we provide papers refined with categories. We also provide common abbreviation of methods after the title with Abbr.

0. Upcoming papers

Here are the accepted papers in SIGMOD2025 in the field of vector search. We are looking forward to following these papers and categorizing them correctly once they are public!

Title	Venue	Authors	Link
SymphonyQG: towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search	Gou et al.	SIGMOD2025
DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph	Yin et al.	SIGMOD2025
Tribase: A Vector Data Query Engine for Reliable and Lossless Pruning Compression using Triangle Inequalities	Xu et al.	SIGMOD2025
Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art	Azizi et al.	SIGMOD2025
Navigating Labels and Vectors: A Unified Approach to Filtered Approximate Nearest Neighbor Search	Cai et al.	SIGMOD2025
Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search	Wei et al.	SIGMOD2025

1. Graph-based

This category collects papers that propose graph-based methods, without combining other three types of categories (e.g., tree-based, hash-based, quantization-based).

Title	Venue	Authors	Link
Approximate nearest neighbor algorithm based on navigable small world graphs (Abbr. NSW)	IS2014	Malkov et al.	link
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (Abbr. HNSW)	TPAMI2018	Malkov et al.	link
Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph (Abbr. NSG)	VLDB2019	Fu et al.	link
High Dimensional Similarity Search with Satellite System Graph: Efficiency, Scalability, and Unindexed Query Compatibility (Abbr. NSSG)	TPAMI2021	Fu et al.	link
Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination	SIGMOD2020	Li et al.	link
Learning to Route in Similarity Graphs	ICML2019	Baranchuk et al.	link
Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search	2024	Lu et al.	link
Reinforcement Routing on Proximity Graph for Efficient Recommendation	TOIS2023	Feng et al.	link
Steiner-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes	VLDB2025	Wang et al.	link
RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search	VLDB2024	Chen et al.	link
ARKGraph: All-Range Approximate K-Nearest-Neighbor Graph	VLDB2023	Zuo et al.	link
EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph	2016	Fu et al.	link
FANNG: Fast Approximate Nearest Neighbour Graphs	CVPR2016	Harwood et al.	link

2. Combining graph and other categories

Title	Venue	Authors	Link
ELPIS: Graph-Based Similarity Search for Scalable Data Science	VLDB2023	Azizi et al.	link
Towards Efficient Index Construction and Approximate Nearest Neighbor Search in High-Dimensional Spaces (Abbr. LSH-APG)	VLDB2023	Zhao et al.	link
HVS: hierarchical graph structure based on voronoi diagrams for solving approximate nearest neighbor search	VLDB2021	Lu et al.	link
Routing-Guided Learned Product Quantization for Graph-Based Approximate Nearest Neighbor Search	ICDE2024	Yue et al.	link

3. Partitions-based and Distributed

Title	Venue	Authors	Link
Learning Space Partitions for Nearest Neighbor Search (Abbr. Neural LSH)	ICLR2020	et al.	link
BLISS: A Billion scale Index using Iterative Re-partitioning	SIGKDD2022	Gupta et al.	link
Learning Balanced Tree Indexes for Large-Scale Vector Retrieval	SIGKDD2023	Li et al.	link
Learned Probing Cardinality Estimation for High-Dimensional Approximate NN Search	ICDE2023	Zheng et al.	link
Learning-based query optimization for multi-probe approximate nearest neighbor search	VLDBJ2023	Zhang et al.	link
SOAR: Improved Indexing for Approximate Nearest Neighbor Search	NIPS2023	Sun et al.	link
Optimizing the Number of Clusters for Billion-Scale Quantization-Based Nearest Neighbor Search	TKDE2024	Fu et al.	link
DIMS: Distributed Index for Similarity Search in Metric Spaces	TKDE2024	Zhu et al.	link
Efficient Distributed Approximate k-Nearest Neighbor Graph Construction by Multiway Random Division Forest	KDD2023	Kim et al.	link
Odyssey: A Journey in the Land of Distributed Data Series Similarity Search	VLDB2023	Chatzakis et al.	link

4. Quantization-based

Title	Venue	Authors	Link
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search	SIGMOD2024	Gao et al.	link
Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search	2024	Gao et al.	link
Similarity Search in the Blink of an Eye with Compressed Indices	VLDB2023	Aguerrebere et al.	link
Model-enhanced Vector Index	NeurIPS2023	Zhang et al.	link
Knowledge Distillation for High Dimensional Search Index	NeurIPS2024	Lu et al.	link
Accelerating Large-Scale Inference with Anisotropic Vector Quantization, ScaNN	ICML2020	Guo et al.	link

5. Hash-based

Title	Venue	Authors	Link
DB-LSH: Locality-Sensitive Hashing with Query-based Dynamic Bucketing	ICDE2023	Tian et al.	link
DB-LSH 2.0: Locality-Sensitive Hashing With Query-Based Dynamic Bucketing	TKDE2023	Tian et al.	link
MP-RW-LSH: an efficient multi-probe LSH solution to ANNS-L1	VLDB2021	Wang et al.	link
PM-LSH: a fast and accurate in-memory framework for high-dimensional approximate NN and closest pair search	VLDB2022	Zheng et al.	link
Query-aware locality-sensitive hashing for approximate nearest neighbor search	VLDB2015	Huang et al.	link
LIDER: an efficient high-dimensional learned index for large-scale dense passage retrieval	VLDB2022	Wang et al.	link
DET-LSH: A Locality-Sensitive Hashing Scheme with Dynamic Encoding Tree for Approximate Nearest Neighbor Search	VLDB2024	Wei et al.	link

6. Tree-based

Title	Venue	Authors	Link
DIDS: Double Indices and Double Summarizations for Fast Similarity Search	VLDB2024	Hu et al.	link
Adaptive Indexing in High-Dimensional Metric Spaces	VLDB2023	Lampropoulos et al.	link
Hercules Against Data Series Similarity Search	VLDB2022	Echihabi et al.	link
Scalable Nearest Neighbor Algorithms for High Dimensional Data	TPAMI2020	Muja et al.	link
i SAX: indexing and mining terabyte sized time series	SIGKDD2008	Shieh et al.	link

7. Disk available

Title	Venue	Authors	Link
DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node	NeurIPS2019	Subramanya et al.	link
DiskANN++: Efficient Page-based Search over Isomorphic Mapped Graph Index using Query-sensitivity Entry Vertex	2023	Ni et al.	link
Filtered − DiskANN: Graph Algorithms for Approximate Nearest Neighbor Search with Filters	Web2023	Gollapudi et al.	link
FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search	2021	Singh et al.	link
SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search	NeurIPS2021	Chen et al.	link
SPFresh: Incremental In-Place Update for Billion-Scale Vector Search	SOSP2023	Xu et al.	link

8. Survey and benchmark

Title	Venue	Authors	Link
A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search	VLDB2021	Wang et al.	link
ParlayANN: Scalable and Deterministic Parallel GraphBased Approximate Nearest Neighbor Search Algorithms	PPoPP2024	Manohar et al.	link
Deep Learning for Approximate Nearest Neighbour Search: A Survey and Future Directions	TKDE2022	Li et al.	link
Survey of Vector Database Management Systems	VLDB2024	Pan et al.	link

9. Hybrid query

Title	Venue	Authors	Link
SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor Search	SIGMOD2024	Zuo et al.	link
ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data	SIGMOD2024	Patel et al.	link
Filtered − DiskANN: Graph Algorithms for Approximate Nearest Neighbor Search with Filters	Web2023	Gollapudi et al.	link
High-Throughput Vector Similarity Search in Knowledge Graphs	SIGMOD2023	Mohoney et al.	link
Navigable Proximity Graph-Driven Native Hybrid Queries with Structured and Unstructured Constraints	2022	Wang et al.	link
AnalyticDB-V: a hybrid analytical engine towards query fusion for structured and unstructured data	VLDB2020	Wei et al.	link

10. Computation acceleration

Title	Venue	Authors	Link
High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations (Abbr. ADSampline)	SIGMOD2023	Gao et al.	link
Accelerating Graph-based Vector Search via Delayed-Synchronization Traversal	2024	Jiang et al.	link
Juno: Optimizing High-Dimensional Approximate Nearest Neighbour Search with Sparsity-Aware Algorithm and Ray-Tracing Core Mapping	ASPLOS2024	Liu et al.	link
FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search	Web2023	Chen et al.	link
Relative NN-Descent: A Fast Index Construction for Graph-Based Approximate Nearest Neighbor Search	MM2023	Ono et al.	link
AdANNS: A Framework for Adaptive Semantic Search	NIPS2023	Rege et al.	link

11. Vector database system

Title	Venue	Authors	Link
Milvus: A Purpose-Built Vector Data Management System	SIGMOD2021	Wang et al.	link
Manu: A Cloud Native Vector Database Management System	VLDB2022	Guo et al.	link
Vexless: A Serverless Vector Data Management System Using Cloud Functions	SIGMOD2024	Su et al.	link
Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment	SIGMOD2024	Wang et al.	link
Efficient Approximate Nearest Neighbor Search in Multi-dimensional Databases	SIGMOD2023	Peng et al.	link
VBASE: Unifying Online Vector Similarity Search and Relational Queries via Relaxed Monotonicity	OSDI2023	Zhang et al.	link
LANNS: a web-scale approximate nearest neighbor lookup system	VLDB2021	Doshi et al.	link
SingleStore-V: An Integrated Vector Database System in SingleStore	VLDB2024	Chen et al.	link

12. Threoratical

Title	Venue	Authors	Link
Graph-based Nearest Neighbor Search: From Practice to Theory	ICML2020	Prokhorenkova et al.	[link]

13. Multi-metric spaces

Title	Venue	Authors	Link
HJG: An Effective Hierarchical Joint Graph for ANNS in Multi-Metric Spaces	ICDE2024	Zhu et al.	[link]

14. Reverse kANN

Title	Venue	Authors	Link
Efficient Reverse k Approximate Nearest Neighbor Search Over High-Dimensional Vectors	ICDE2024	Song et al.	[link]

Papers Refined with Research Groups

In this section, we provide papers refined with research groups.

• Yury Malkov, OpenAI

  1. Approximate nearest neighbor algorithm based on navigable small world graphs (IS2014), Malkov et al. [link]
  2. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (TPAMI2018), Malkov et al. [link]

• Zilliz

  1. Milvus: A Purpose-Built Vector Data Management System (SIGMOD2021), Wang et al. [link]
  2. Manu: A Cloud Native Vector Database Management System (VLDB2022), Guo et al. [link]
  3. Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment (SIGMOD2024), Wang et al. [link]

• Qi Chen, Microsoft Research

  1. SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search (NeurIPS2021), Chen et al. [link]
  2. SPFresh: Incremental In-Place Update for Billion-Scale Vector Search (SOSP2023), Xu et al. [link]
  3. VBASE: Unifying Online Vector Similarity Search and Relational Queries via Relaxed Monotonicity (OSDI2023), Zhang et al. [link]

• Dong Deng, Rutgers University

  1. SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor Search (SIGMOD2024), Zuo et al. [link]
  2. ARKGraph: All-Range Approximate K-Nearest-Neighbor Graph (VLDB2023), Zuo et al. [link]

• Cong Fu, Zhejiang University

  1. EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph (2016), Fu et al. [link]
  2. Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph (VLDB2019), Fu et al. [link]

• Kejing Lu, Nagoya University

  1. Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search (2024), Lu et al. [link]
  2. HVS: hierarchical graph structure based on voronoi diagrams for solving approximate nearest neighbor search (VLDB2021), Lu et al. [link]

• Defu Lian, University of Science and Technology of China

  1. Knowledge Distillation for High Dimensional Search Index (NeurIPS2024), Lu et al. [link]
  2. Reinforcement Routing on Proximity Graph for Efficient Recommendation (TOIS2023), Feng et al. [link]
  3. Learning Balanced Tree Indexes for Large-Scale Vector Retrieval (SIGKDD2023), Li et al. [link]

• Themis Palpanas, LIPADE, Université Paris Cité

  1. Steiner-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes (VLDB2025), Wang et al. [link]
  2. ELPIS: Graph-Based Similarity Search for Scalable Data Science (VLDB2023), Azizi et al. [link]
  3. Hercules Against Data Series Similarity Search (VLDB2022), Echihabi et al. [link]
  4. DET-LSH: A Locality-Sensitive Hashing Scheme with Dynamic Encoding Tree for Approximate Nearest Neighbor Search (VLDB2024), Wei et al. [link]

• Guoliang Li, Tsinghua University

  1. Survey of Vector Database Management Systems (VLDB2024), Pan et al. [link]

• Bin Cui, Peking University

  1. Model-enhanced Vector Index (NeurIPS2023), Zhang et al. [link]

• Xi Zhao, Xiaofang Zhou, Hong Kong University of Science and Technology

  1. Towards Efficient Index Construction and Approximate Nearest Neighbor Search in High-Dimensional Spaces (VLDB2023), Zhao et al. [link]
  2. DB-LSH: Locality-Sensitive Hashing with Query-based Dynamic Bucketing (ICDE2023), Tian et al. [link]
  3. DB-LSH 2.0: Locality-Sensitive Hashing With Query-Based Dynamic Bucketing (TKDE2023), Tian et al. [link]

• Xiaoliang Xu, Yuxiang Wang, Hangzhou Dianzi University

  1. Routing-Guided Learned Product Quantization for Graph-Based Approximate Nearest Neighbor Search (ICDE2024), Yue et al. [link]
  2. DiskANN++: Efficient Page-based Search over Isomorphic Mapped Graph Index using Query-sensitivity Entry Vertex (2023), Ni et al. [link]
  3. Navigable Proximity Graph-Driven Native Hybrid Queries with Structured and Unstructured Constraints (2022), Wang et al. [link]
  4. Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment (SIGMOD2024), Wang et al. [link]

• Jianyang Gao, Cheng Long, Nanyang Technological University

  1. RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search (SIGMOD2024), Gao et al. [link]
  2. High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations (SIGMOD2023), Gao et al. [link]

• Wei Wang, Fudan University

  1. Steiner-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes (VLDB2025), Wang et al. [link]

• Wei Wang, Hong Kong University of Science and Technology (Guangzhou)

  1. Deep Learning for Approximate Nearest Neighbour Search: A Survey and Future Directions (TKDE2022), Li et al. [link]

• Pengcheng Zhang, Bin Yao, Shanghai Jiao Tong University

  1. Learning-based query optimization for multi-probe approximate nearest neighbor search (VLDBJ2023), Zhang et al. [link]

• Bolong Zheng, Huazhong University of Science and Technology

  1. Learned Probing Cardinality Estimation for High-Dimensional Approximate NN Search (ICDE2023), Zheng et al. [link]
  2. PM-LSH: a fast and accurate in-memory framework for high-dimensional approximate NN and closest pair search (VLDB2022), Zheng et al. [link]

• Jianguo Wang, Purdue University

  1. Vexless: A Serverless Vector Data Management System Using Cloud Functions (VLDB2024), Su et al. [link]

• Lu Chen, Zhejiang University

  1. HJG: An Effective Hierarchical Joint Graph for ANNS in Multi-Metric Spaces (ICDE2024), Zhu et al. [link]

• Bin Yao, Shanghai Jiao Tong University

  1. Efficient Reverse k Approximate Nearest Neighbor Search Over High-Dimensional Vectors (ICDE2024), Song et al. [link]