ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2403.04871/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data — mentioned by VoVAllenhttps://news.ycombinator.com/item?id=42499471urn:hackerpapers:mention:2403.04871:42499471Tue, 24 Dec 2024 03:19:26 GMT<p>Hi, I&#x27;m the author of the article. I actually think the opposite of what you mentioned. IVF is more suitable for prefiltering compared to HNSW. For prefiltering in HNSW, there is a certain requirement for the filtering rate—it can&#x27;t be too low, or the entire graph may become disconnected. For instance, with the commonly used parameter m=16, each node can have at most 16 neighbors. If the filtering rate is below 5%, it can directly result in no neighbors meeting the condition, causing the algorithm to fail entirely. This is why the academic community has proposed alternatives like ACRON[1]. On…</p><p><a href="https://hackerpaper.kaipfister.de/p/2403.04871/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.IR