benwtrent commented on PR #13566: URL: https://github.com/apache/lucene/pull/13566#issuecomment-2276247855
> or maybe you're suggesting we change the way we search, not specifically something about this patch? That does kind of make sense to me - I'm not sure why the HNSW paper settled on a single node at each level ^ This is what I am thinking. maybe select a logarithmically scaled number entry points when compared to the number of nearest neighbors that are being searched? This might mean its usually just 1, but maybe this is OK? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
