SOAR: Improved Indexing for Approximate Nearest Neighbor Search

Published: 21 Sept 2023, Last Modified: 07 Dec 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: ann, quantization, mips, nearest neighbor search, retrieval
Abstract: This paper introduces SOAR: **S**pilling with **O**rthogonality-**A**mplified **R**esiduals, 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.
Supplementary Material: zip
Submission Number: 3379