SOAR: Improved Indexing for Approximate Nearest Neighbor Search

arXiv:2404.00774v1 Announce Type: new
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 …

abstract ann approximate nearest neighbor arxiv cs.lg data indexing multiple novel paper partitioning probability reduce search soar trees type