Sparcent: faster multi-vector dense retrieval with sparse centroid indices
Knowledge and Information Systems, cilt.68, sa.1, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 68 Sayı: 1
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s10115-026-02907-x
- Dergi Adı: Knowledge and Information Systems
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, ABI/INFORM, Aerospace Database, Applied Science & Technology Source, Compendex, INSPEC, Engineering Source (EBSCO), Pharma Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: Multi-vector dense retrieval, Neural information retrieval, Retrieval efficiency, Sparse retrieval
- Orta Doğu Teknik Üniversitesi Adresli: Evet
Özet
Multi-vector dense retrieval methods have set the state-of-the-art retrieval quality on ranking tasks. However, the superior effectiveness of such methods comes with substantial computational overhead, which makes their deployment in large-scale search engines infeasible. As a remedy, we propose a novel approach, Sparcent, that leverages learned sparse retrieval (LSR) to accelerate the query-centroid matching stage in multi-vector dense retrieval. Specifically, we first derive sparse centroid representations for multi-vector term-embedding clusters and then prune them, producing compact centroid vectors that remain both efficient and effective for the indexing via LSR methods. Next, we integrate Sparcent with two well-known multi-vector retrieval systems, PLAID and WARP, already optimized for single-core CPU search. Our experimental results show that Sparcent provides up to 4.6× speed-up over the original PLAID and 1.3× speed-up over WARP, respectively, with virtually zero additional memory, while maintaining result effectiveness on both in-domain and out-of-domain retrieval tasks.