Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor SearchDownload PDF

Published: 31 Oct 2022, Last Modified: 12 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: Approximate nearest neighbor search, locality-sensitive, recall-speed tradeoff
Abstract: We present Falconn++, a novel locality-sensitive filtering (LSF) approach for approximate nearest neighbor search on angular distance. Falconn++ can filter out potential far away points in any hash bucket before querying, which results in higher quality candidates compared to other hashing-based solutions. Theoretically, Falconn++ asymptotically achieves lower query time complexity than Falconn, an optimal locality-sensitive hashing scheme on angular distance. Empirically, Falconn++ achieves a higher recall-speed tradeoff than Falconn on many real-world data sets. Falconn++ is also competitive with HNSW, an efficient representative of graph-based solutions on high search recall regimes.
TL;DR: We present Falconn++, a novel locality-sensitive filtering approach for approximate nearest neighbor search on angular distance.
Supplementary Material: pdf
19 Replies

Loading