AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs

Yu. A. Malkov, Dmitry A. Yashunin

TPAMI 2018 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 2,570 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use exponential layer assignment with mL=1/ln(M) instead of mL=0 (single layer) (ablation)Hierarchical NSW · 10M random d=4 vectorsquery time at fixed recallImproved
add hierarchy (mL>0) on very high dimensional data (ablation)Hierarchical NSW · 100k random d=1024 vectorsquery time at fixed recallImproved
use neighbor selection heuristic instead of closest neighbors (ablation)Hierarchical NSW · clustered and low-dimensional dataquery time at fixed recallImproved
use neighbor selection heuristic instead of closest neighbors (ablation)Hierarchical NSW · uniform very high dimensional dataquery time at fixed recallNo clear effect
set Mmax0 to 2*M instead of M (ablation)Hierarchical NSW · 5M SIFT learnquery time at fixed recallImproved
raise Mmax0 above 2*M (ablation)Hierarchical NSW · 5M SIFT learnquery time at fixed recallHurt
use larger M (ablation)Hierarchical NSW · high recall / high dimensional dataquery time at fixed recallMixed
raise efConstruction beyond 100 (ablation)Hierarchical NSW · 10M SIFTindex quality vs build timeNo clear effect
add hierarchical layers to NSW (ablation)NSW baseline · d=4 and d=8 random hypercubequery time at fixed recallImproved
add hierarchical layers to NSW (ablation)NSW baseline · Wiki-8 JS-divergence (general space)distance computations: almost 3 orders of magnitudeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

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