mlsanityData to 7 Oct 2026

SOAR: Improved Indexing for Approximate Nearest Neighbor Search

arXiv 2404.00774 ↗First posted 31 Mar 2024cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, a novel data indexing technique for approximate nearest neighbor (ANN) search. SOAR extends upon previous approaches to ANN search, such as spill trees, that utilize multiple redundant representations while partitioning the data to reduce the probability of missing a nearest neighbor during search. Rather than training and computing these redundant representations independently, however, SOAR uses an orthogonality-amplified residual loss, which optimizes each representation to compensate for cases where other representations perform poorly. This drastically improves the overall index quality, resulting in state-of-the-art ANN benchmark performance while maintaining fast indexing times and low memory consumption.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 31 Mar 2024.

Builds on

7 of 16 references.

References · 7

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  4. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  5. 2018ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithmscited by 130
  6. 2014Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)cited by 109
  7. 2022Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Searchcited by 45

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 5.

12 papers.

  1. 2025Quake: Adaptive Indexing for Vector Searchcited by 8
  2. 2024LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Searchcited by 4
  3. 2025Synthetic bootstrapped pretrainingcited by 4
  4. 2025Studying Classifier(-Free) Guidance From a Classifier-Centric Perspectivecited by 1
  5. 2025SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAGcited by 1
  6. 2026Amortized Maximum Inner Product Search with Learned Support Functionscited by 1
  7. 2025Infinity Search: Approximate Vector Search with Projections on q-Metric Spacescited by 0
  8. 2025Large-Scale Graph Building in Dynamic Environments: Low Latency and High Qualitycited by 0
  9. 2026Welfarist Formulations for Diverse Similarity Searchcited by 0
  10. 2026SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor frameworkcited by 0
  11. 2026PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generationcited by 0
  12. 2026Region-Aware CLS Token Augmentation for Fine-Grained Image Retrievalcited by 0