NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction
Ranking
Overall
79
Content
95
Popularity
41
Observed public metrics from 1 member.
Merged summary
TL;DR - NeuRoute is a learned hashing index that uses neural encoder logits to route queries efficiently in billion-scale approximate nearest-neighbor search. It delivers competitive recall and throughput while reducing end-to-end index construction to under an hour.
- Produces balanced binary addresses using a lightweight encoder and a selective similarity-preserving objective.
- Uses logit uncertainty to prioritize adaptive multi-bucket probing, then applies centroid gating and early stopping.
- Achieves 90.3% Recall@10 at 2,414 QPS on BigANN-1B.
- Runs 1.7Ă— faster than OPQ+IVF-PQ refinement at comparable accuracy and builds indexes for BigANN-1B and Deep1B-1B in under an hour.
Sources (1)
NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - NeuRoute is a learned hashing index that uses neural encoder logits to route queries efficiently in billion-scale approximate nearest-neighbor search. It delivers competitive recall and throughput while reducing end-to-end index construction to under an hour.
- Produces balanced binary addresses using a lightweight encoder and a selective similarity-preserving objective.
- Uses logit uncertainty to prioritize adaptive multi-bucket probing, then applies centroid gating and early stopping.
- Achieves 90.3% Recall@10 at 2,414 QPS on BigANN-1B.
- Runs 1.7Ă— faster than OPQ+IVF-PQ refinement at comparable accuracy and builds indexes for BigANN-1B and Deep1B-1B in under an hour.