AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

AdANNS: A Framework for Adaptive Semantic Search

Aniket Rege, Aditya Kusupati, Sharan Ranjit S, Alan Fan, Qingqing Cao, Sham M. Kakade, Prateek Jain, Ali Farhadi

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Learned embeddings for retrieval · 2 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
decouple clustering dimension d_c from scan dimension d_s using matryoshka representationsIVF · ImageNet-1K retrievaltop-1 accuracy: 68.51 -> 70.02Improved
use AdANNS-IVF instead of rigid IVF at matched computeIVF · ImageNet-1K retrievalcompute: up to 100x lesser FLOPS/queryImproved
matryoshka instead of rigid representation for IVFIVF · ImageNet-1Kaccuracy-compute trade-offImproved
post-hoc SVD compression of rigid representation instead of matryoshkaIVF/OPQ · ImageNet-1Ktop-1 accuracyHurt
AdANNS-OPQ with matryoshka instead of OPQ on rigidOPQ · ImageNet-1Ktop-1 accuracy: up to 4%Improved
AdANNS-OPQ at 32 bytes vs rigid OPQ at 64 bytesOPQ · ImageNet-1Kstorage and FLOPS: 64 bytes -> 32 bytesImproved
AdANNS-IVFOPQ composite indexIVFOPQ · ImageNet-1Ktop-1 accuracy: 1-4%Improved
AdANNS-DiskANN with 8-byte OPQDiskANN · ImageNet-1Kcost: 32 -> 8 bytesImproved
replace PQ with OPQ at large dimensionexact search · ImageNet-1K d=2048, m=8top-1 accuracy: 62.19 -> 66.89Improved
replace PQ with OPQ at small dimensionexact search · ImageNet-1K d=64, m=8top-1 accuracy: 68.39 -> 68.38No clear effect
use low-dimensional matryoshka prefix for scan on index built with 2048-d (AdANNS-IVF-D)IVF · ImageNetV2, d=8top-1 accuracy: 50.44 -> 53.51Improved
AdANNS-IVF-D at high dimensionIVF · ImageNetV2, d=2048top-1 accuracy: 58.04 -> 58.04No clear effect

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