An Experimental Evaluation of Hybrid Querying on Vectors
Summary: Comprehensive evaluation and taxonomy of 15 hybrid vector+structured-filtering query algorithms, introducing standardized attribute/range benchmarks and classifying methods by index organization and filtering strategy. Large-scale (100M) cross-platform experiments compare build/query costs and robustness across distributions, yielding strengths/weaknesses, practical algorithm-selection guidelines, and directions for improvement. (summarized by gpt-5-mini on Mar 13 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jiaxu Zhu (Huazhong University of Science and Technology)
- 2. Jiayu Yuan (Huazhong University of Science and Technology)
- 3. Kaiwen Yang (Huazhong University of Science and Technology)
- 4. Xiaobao Chen (Huazhong University of Science and Technology)
- 5. Shihuan Yu (Huazhong University of Science and Technology)
- 6. Hongchang Lv (Huazhong University of Science and Technology)
- 7. Yan Li (Wuhan University)
- 8. Bolong Zheng (Huazhong University of Science and Technology)
BibTeX Citation
@article{zhu_vldb26,
title = {{An Experimental Evaluation of Hybrid Querying on Vectors}},
author = {Zhu, Jiaxu and Yuan, Jiayu and Yang, Kaiwen and Chen, Xiaobao and Yu, Shihuan and Lv, Hongchang and Li, Yan and Zheng, Bolong},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {2},
pages = {183--195},
doi = {10.14778/3773749.3773757},
url = {https://doi.org/10.14778/3773749.3773757},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Outgoing Citations (Sorted by Pagerank)
Showing 15 of 15 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,163 | Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study | 2026 | SIGMOD |
| 2 | 10,449 | Efficient Vector Index Merging in Vector Databases | 2026 | SIGMOD |
| 3 | 12,331 | Answering Top-k Queries Over a Mixture of Attractive and Repulsive Dimensions | 2012 | VLDB |
| 4 | 10,984 | Benchmarking Adaptive Multidimensional Indices | 2025 | VLDB |
| 5 | 10,346 | Beyond Vector Search: Querying With and Without Predicates | 2026 | SIGMOD |
| 6 | 1,631 | High-Throughput Vector Similarity Search in Knowledge Graphs | 2023 | SIGMOD |
| 7 | 7,843 | BigVectorBench: Heterogeneous Data Embedding and Compound Queries are Essential in Evaluating Vector Databases | 2025 | VLDB |
| 8 | 10,563 | Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search | 2026 | VLDB |
| 9 | 10,304 | VecBench: A Controllable Benchmark for Filtered Vector Search: [Experiments & Analysis] | 2026 | SIGMOD |
| 10 | 3,240 | Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art | 2025 | SIGMOD |