An Empirical Comparison of FAISS and FENSHSES for Nearest Neighbor Search in Hamming Space
arXiv:1906.10095
The paper empirically compares FAISS and FENSHSES for nearest neighbor search in Hamming space, evaluating indexing speed, query latency, and memory usage to understand trade‑offs between main‑memory and secondary‑memory implementations.
Abstract
In this paper, we compare the performances of FAISS and FENSHSES on nearest neighbor search in Hamming space--a fundamental task with ubiquitous applications in nowadays eCommerce. Comprehensive evaluations are made in terms of indexing speed, search latency and RAM consumption. This comparison is conducted towards a better understanding on trade-offs between nearest neighbor search systems implemented in main memory and the ones implemented in secondary memory, which is largely unaddressed in literature.
SIGIR eCom'19