REWEAVE rewires HNSW vector indexes online, boosting recall by up to 23.3 points
_reachsumit · x · 2026-11-13
REWEAVE (arXiv:2611.16060) is an online index-maintenance method that learns HNSW edge utility from query feedback and periodically rewires the bottom layer within the same per-node degree cap. Under skewed or drifting workloads it improves held-out recall by up to 23.3 points over standard HNSW; at 100M vectors it reaches 3.3x NGFix's query throughput at recall@100 of 0.80; on Amazon-ESCI with query drift it lifts stream recall@100 from 0.745 to 0.979 with 34% fewer distance computations.
More from Research
- Ex-Moonshot AI researcher startup uses AI to automate chip formal verification — teortaxesTex · 2026-11-13
- MIT's Markus Buehler Launches Applied AI for Materials Discovery Short Course — ProfBuehlerMIT · 2026-11-13
- From-scratch 42M-parameter model handles 7 African languages, runs offline on phones — AgencyInside407 · 2026-11-13
- Aristotle Formal Verification Proves bunnie's Security Chip Conforms to RISC-V SAIL Spec — satnam6502 · 2026-11-13
- Harvard open-sources its entire ML Systems curriculum — free, 6 pillars, hundreds of pages — mdancho84 · 2026-11-13
- 1960 Science paper famously predicted doomsday on Nov 13, 2026 — voxleone · 2026-11-13