Work Sharing and Offloading for Efficient Approximate Threshold-based Vector Join
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910056135524352 |
|---|---|
| author | Kim, Kyoungmin Roth, Lennart Liang, Liang Ailamaki, Anastasia |
| author_facet | Kim, Kyoungmin Roth, Lennart Liang, Liang Ailamaki, Anastasia |
| contents | Vector joins - finding all vector pairs between a set of query and data vectors whose distances are below a given threshold - are fundamental to modern vector and vector-relational database systems that power multimodal retrieval and semantic analytics. Existing state-of-the-art approach exploits work sharing among similar queries but still suffers from redundant index traversals and excessive distance computations. We propose a unified framework for efficient approximate vector joins that (1) introduces soft work sharing to reuse traversal results beyond the join results of previous queries, (2) builds a merged index over both query and data vectors to further speedup graph explorations, and (3) improves robustness for out-of-distribution queries through an adaptive hybrid search strategy. Experiments on eight datasets demonstrate substantial improvements in efficiency-recall trade-off over the state of the art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16360 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Work Sharing and Offloading for Efficient Approximate Threshold-based Vector Join Kim, Kyoungmin Roth, Lennart Liang, Liang Ailamaki, Anastasia Databases Vector joins - finding all vector pairs between a set of query and data vectors whose distances are below a given threshold - are fundamental to modern vector and vector-relational database systems that power multimodal retrieval and semantic analytics. Existing state-of-the-art approach exploits work sharing among similar queries but still suffers from redundant index traversals and excessive distance computations. We propose a unified framework for efficient approximate vector joins that (1) introduces soft work sharing to reuse traversal results beyond the join results of previous queries, (2) builds a merged index over both query and data vectors to further speedup graph explorations, and (3) improves robustness for out-of-distribution queries through an adaptive hybrid search strategy. Experiments on eight datasets demonstrate substantial improvements in efficiency-recall trade-off over the state of the art. |
| title | Work Sharing and Offloading for Efficient Approximate Threshold-based Vector Join |
| topic | Databases |
| url | https://arxiv.org/abs/2603.16360 |