SOAR: Improved Indexing for Approximate Nearest Neighbor Search
Philip Sun, David Simcha, Dave Dopson, Ruiqi Guo, Sanjiv Kumar

TL;DR
SOAR introduces an innovative indexing method for approximate nearest neighbor search that leverages orthogonality-amplified residuals to enhance index quality, achieving state-of-the-art results with efficient resource use.
Contribution
The paper presents SOAR, a novel ANN indexing technique that optimizes multiple representations jointly using orthogonality-amplified residuals, improving search accuracy and efficiency.
Findings
Achieves state-of-the-art ANN benchmark performance.
Maintains fast indexing times and low memory consumption.
Significantly improves index quality over previous methods.
Abstract
This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsData Management and Algorithms · Advanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques
