Skip to main content
Search

# Hybrid Dense-Sparse Vector Retrieval

1 related articles

Subscribe to updates
  1. arXiv

    Hybrid retrieval stops rebuilding per query weight: UniGraph merges neighborhoods from several weights into one graph and lifts QPS 27.6%–52.3% over the fastest baseline under mixed weights

    Dense vectors capture semantics and sparse vectors keep lexical terms, and hybrid retrieval ranks items by a query-dependent weighted sum of the two distances; existing systems either search separate dense and sparse indexes and rerank the union, or build one graph at a fixed weight whose neighborhoods shift when the weight changes. UniGraph samples neighbors at multiple weights, merges them by selection frequency into one bounded-degree graph, routes each query to a sparse- or dense-guided entry point, and uses dense-first distance pruning to skip some exact sparse computations. On five BEIR datasets under mixed weights, it delivers 27.6%–52.3% higher QPS than the fastest baseline at Recall@100 without index reconstruction.

You’re all caught up