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.

Falconn++ is also competitive with HNSW, an efficient representative of graph-based solutions on high search recall regimes.

Falconn++ is also competitive with HNSW, an efficient representative of graph-based solutions on high search recall regimes.

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.

Algorithms for approximate nearest-neighbor search (ANNS) have been the topic of significant recent interest in the research community. However, evaluations of such algorithms are usually restricted to a small number of datasets with millions or tens of millions of points, whereas real-world applications require algorithms that work on the scale of billions of points. Furthermore, existing evaluations of ANNS algorithms are typically heavily focused on measuring and optimizing for queries-per second (QPS) at a given accuracy, which can be hardware-dependent and ignores important metrics such as build time. In this paper, we propose a set of principled measures for evaluating ANNS algorithms which refocuses on their scalability to billion-size datasets. These measures include ability to be efficiently parallelized, build times, and scaling relationships as dataset size increases. We also expand on the QPS measure with machine-agnostic measures such as the number of distance computations per query, and we evaluate ANNS data structures on their accuracy in more demanding settings required in modern applications, such as evaluating range queries and running on out-of-distribution data. We optimize four graph-based algorithms for the billion-scale setting, and in the process provide a general framework for making many incremental ANNS graph algorithms lock-free. We use our framework to evaluate the aforementioned graph-based ANNS algorithms as well as two alternative approaches.