mlsanityData to 7 Oct 2026

Similarity search in the blink of an eye with compressed indices

arXiv 2304.04759 ↗First posted 7 Apr 2023cs.LG cs.IRcited by 20

Not on the map. Why?

Abstract (arXiv)

Nowadays, data is represented by vectors. Retrieving those vectors, among millions and billions, that are similar to a given query is a ubiquitous problem, known as similarity search, of relevance for a wide range of applications. Graph-based indices are currently the best performing techniques for billion-scale similarity search. However, their random-access memory pattern presents challenges to realize their full potential. In this work, we present new techniques and systems for creating faster and smaller graph-based indices. To this end, we introduce a novel vector compression method, Locally-adaptive Vector Quantization (LVQ), that uses per-vector scaling and scalar quantization to improve search performance with fast similarity computations and a reduced effective bandwidth, while decreasing memory footprint and barely impacting accuracy. LVQ, when combined with a new high-performance computing system for graph-based similarity search, establishes the new state of the art in terms of performance and memory footprint. For billions of vectors, LVQ outcompetes the second-best alternatives: (1) in the low-memory regime, by up to 20.7x in throughput with up to a 3x memory footprint reduction, and (2) in the high-throughput regime by 5.8x with 1.4x less memory.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 26 of its 63 references that are in the map. First posted on arXiv 7 Apr 2023.

Builds on

26 of 63 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  7. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  8. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  9. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  10. 2018ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithmscited by 130
  11. 2016A Survey on Learning to Hashcited by 119
  12. 2017Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graphcited by 103
14 more
  1. 2021A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Searchcited by 82
  2. 2021Everything at Once -- Multi-modal Fusion Transformer for Video Retrievalcited by 79
  3. 2021VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inferencecited by 59
  4. 2022Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Searchcited by 45
  5. 2016Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)cited by 44
  6. 2021A Survey on Locality Sensitive Hashing Algorithms and their Applicationscited by 40
  7. 2022Semi-Parametric Neural Image Synthesiscited by 36
  8. 2022Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Trainingcited by 26
  9. 2018Optimization of Indexing Based on k-Nearest Neighbor Graph for Proximity Search in High-dimensional Datacited by 20
  10. 2018Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMDcited by 14
  11. 2016Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertisingcited by 12
  12. 2021Low-Precision Quantization for Efficient Nearest Neighbor Searchcited by 6
  13. 2021Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Searchcited by 5
  14. 2022Speed-ANN: Low-Latency and High-Accuracy Nearest Neighbor Search via Intra-Query Parallelismcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 10; 2026: 6.

20 papers.

Sort:

By area:

  1. 2024Arctic-Embed 2.0: Multilingual Retrieval Without Compromisecited by 57
  2. 2025PDX: A Data Layout for Vector Similarity Searchcited by 8
  3. 2025VIBE: Vector Index Benchmark for Embeddingscited by 6
  4. 2023LeanVec: Searching vectors faster by making them fitcited by 5
  5. 2025RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithmcited by 5
  6. 2025Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Searchcited by 4
  7. 2024Down with the Hierarchy: The 'H' in HNSW Stands for "Hubs"cited by 3
  8. 2025Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learningcited by 3
  9. 2025HAKES: Scalable Vector Database for Embedding Search Servicecited by 2
  10. 2025An Entity Linking Agent for Question Answeringcited by 2
  11. 2026ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMscited by 2
  12. 2025Bang for the Buck: Vector Search on Cloud CPUscited by 1
8 more
  1. 2024GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reductioncited by 0
  2. 2025Scalable k-Means Clustering for Large k via Seeded Approximate Nearest-Neighbor Searchcited by 0
  3. 2025Individualized non-uniform quantization for vector searchcited by 0
  4. 2026Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph Approachcited by 0
  5. 2026FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Searchcited by 0
  6. 2026MERIT: Efficient In-Place Deletion for Dynamic Graph-Based Approximate Nearest Neighbor Indexescited by 0
  7. 2026Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddingscited by 0
  8. 2026RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Searchcited by 0