AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint

Mengzhao Wang, Lingwei Lv, Xiaoliang Xu, Yuxiang Wang, Qiang Yue, Jiongkang Ni

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Learned embeddings for retrieval · 7 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 NHQ joint-pruning composite index instead of AF-then-ANNSDiskANN · BIGANN100M, Recall@10=0.95QPS: 315×Improved
use NHQ instead of AF-then-ANNSDiskANN · BIGANN100M, Recall@10=0.95mean disk I/Os: 1,303 -> 30Improved
use our edge selection instead of HCNNG/NSG (ablation)NPG edge selection · SIFT1M, Recall@10=0.9speedup: 1.1×Improved
use our edge selection instead of HNSW (ablation)NPG edge selection · SIFT1M, Recall@10=0.9speedup: 1.4×Improved
use our edge selection instead of NGT (ablation)NPG edge selection · SIFT1M, Recall@10=0.9speedup: 25.9×Improved
use our routing strategy instead of plain HNSW routing (ablation)HNSW index · SIFT1M, Recall@10=0.9speedup vs HNSW: 1.00 -> 1.21Improved
use TOGG routing (ablation)HNSW index · SIFT1M, Recall@10=0.9speedup vs HNSW: 1.00 -> 1.20Improved
use FINGER routing (ablation)HNSW index · SIFT1M, Recall@10=0.9speedup vs HNSW: 1.00 -> 1.30Mixed
use HCNNG routing (ablation)HNSW index · SIFT1M, Recall@10=0.9speedup vs HNSW: 1.00 -> 1.02No clear effect
apply NHQ (Strategy C) to HNSW and NSG (ablation)HNSW, NSG · SIFT1MQPS vs Recall@10Improved
use PQ-based IVFPQ with Strategy A instead of PG (ablation)IVFPQ · SIFT1MRecall@10Hurt
use NPGkgraph instead of HNSW or NSG within NHQ (ablation)NHQ · SIFT1M and GloVeQPS vs Recall@10Improved

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