Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search
This work addresses the problem of efficient nearest neighbor search for applications like recommendation systems, offering incremental improvements over existing hashing-based methods.
The paper tackles approximate nearest neighbor search on angular distance by introducing Falconn++, a locality-sensitive filtering approach that filters out far points before querying, achieving higher recall-speed tradeoffs than Falconn and competitive performance with HNSW in high recall regimes.
We present Falconn++, a novel locality-sensitive filtering approach for approximate nearest neighbor search on angular distance. Falconn++ can filter out potential far away points in any hash bucket \textit{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 higher recall-speed tradeoffs 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.