An Empirical Comparison of FAISS and FENSHSES for Nearest Neighbor Search in Hamming Space
This work addresses a gap in understanding memory trade-offs for nearest neighbor search, relevant to eCommerce applications, but is incremental as it focuses on empirical comparison.
The paper compared FAISS and FENSHSES for nearest neighbor search in Hamming space, finding differences in indexing speed, search latency, and RAM consumption to highlight trade-offs between main and secondary memory implementations.
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.