An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments & Analysis]
Summary: Production PostgreSQL study of filter-agnostic filtered vector search across selectivities and correlations, comparing post- versus inline-filtering. Shows page-access and filter-check overheads can outweigh distance costs: ScaNN may beat graph indexes, with choices determined by workload and system costs. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Duo Lu (Brown University)
- 2. Helena Caminal (Google)
- 3. Manos Chatzakis (Université Paris Cité)
- 4. Yannis Papakonstantinou (Google)
- 5. Yannis Chronis (ETH Zurich; Google)
- 6. Vaibhav Jain (Google)
- 7. Fatma Özcan (Google)
BibTeX Citation
@inproceedings{lu_sigmod26,
title = {{An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments \& Analysis]}},
author = {Lu, Duo and Caminal, Helena and Chatzakis, Manos and Papakonstantinou, Yannis and Chronis, Yannis and Jain, Vaibhav and Özcan, Fatma},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802011},
url = {https://dl.acm.org/doi/10.1145/3802011},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 23 of 23 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 8,872 | Cost-Effective, Low Latency Vector Search with Azure Cosmos DB | 2025 | VLDB |
| 2 | 1,065 | PASE: PostgreSQL Ultra-High-Dimensional Approximate Nearest Neighbor Search Extension | 2020 | SIGMOD |
| 3 | 8,205 | VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search | 2025 | VLDB |
| 4 | 3,240 | Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art | 2025 | SIGMOD |
| 5 | 10,571 | An Experimental Evaluation of Hybrid Querying on Vectors | 2026 | VLDB |
| 6 | 10,304 | VecBench: A Controllable Benchmark for Filtered Vector Search: [Experiments & Analysis] | 2026 | SIGMOD |
| 7 | 8,782 | Filtered Vector Search: State-of-the-art and Research Opportunities | 2025 | VLDB |
| 8 | 8,169 | NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance | 2025 | VLDB |
| 9 | 9,778 | Turbocharging Vector Databases using Modern SSDs | 2025 | VLDB |
| 10 | 8,781 | Fast Vector Search in PostgreSQL: A Decoupled Approach | 2026 | CIDR |