AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Approximate nearest neighbor indexing

Build graph and partition indexes for fast approximate nearest neighbor search with guarantees.

58 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Prediction and decision losses, keyword cluster “ranking · nearest · neighbor”

State History Tried Checklist Preprints Who Export

Where it stands

Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.

9 papers in 2023–24 and 16 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 1.7% to 2.8%.

How this is decided

A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.

How it got here

2016: 5162017: 2172018: 10182019: 6192020: 3202021: 2212022: 5222023: 6232024: 3242025: 8252026: 826

Most cited paper of each year

Earliest papers here

What has been tried

49 papers here report 426 measured changes (a component added, removed or swapped, compared with a baseline): helped 65%, no clear effect 11%, hurt 19%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

What was changedMeasured onResultEffectPaper
Add weighted kNN classification using SamHub-estimated k-occurrencesCNAE, Mini-ngs, Gisette, Optdigits · accuracyHelpedOn Finding Hubs in High Dimensions with Sampling (AAAI 2025 · 1 citation)
Learn data rankings rather than freeze the data-processing network1D uniform · accuracyHelpedDiscovering Data Structures: Nearest Neighbor Search and Beyond (NeurIPS 2025 · 0 citations)
Increase branching factor βSIFT, filter fraction 2^-1 · recallHurtApproximate Nearest Neighbor Search with Window Filters (ICML 2024 · 0 citations)

What reviewers will expect

Datasets and baselines named in the 11 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Datasets

  • MNIST · 3 of 11 papers
  • Diabetes · 2 of 11 papers
  • Optdigits · 2 of 11 papers
  • Adult · 2 of 11 papers
  • SIFT · 2 of 11 papers

Baselines

  • KMeans · 2 of 11 papers
  • NeuralLSH · 2 of 11 papers

Recent preprints

Loading recent arXiv preprints…

    Who publishes on it

    Institutions on the most papers of this approach since 2023 (of 25 papers; from OpenAlex and the papers' affiliations).

    Use it

    Download BibTeX of 39 key papersOpen the topic in the interactive map

    Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.

    Same keyword cluster

    Elsewhere in the topic

    Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).

    Get the next scime Dispatch and a monthly field update

    Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy