Hi! The implementation of the HNSW algorithm in MariaDB is not identical to the paper (hence the m from modified or MariaDB in mHNSW).
You should *not* try to compare against equal M / ef_search values of other implementations, but rather compare QPS for a particular Recall target (say 95%, 98%, 99%) That will give you an apples-to-apples comparison. Vicențiu On Wed, 19 Feb 2025 at 14:46, shiyer22--- via discuss < [email protected]> wrote: > Thanks Sergei! Is it possible to let me know the internally decided > ef_construction value? That will help me in putting recall results in > context with other benchmarks. Is the ef_construction computed based on M / > dimension etc? > _______________________________________________ > discuss mailing list -- [email protected] > To unsubscribe send an email to [email protected] >
_______________________________________________ discuss mailing list -- [email protected] To unsubscribe send an email to [email protected]
