PDX: A Data Layout for Vector Similarity Search

Summary: PDX stores multiple vectors in vertical blocks across dimensions, enabling a dimension-by-dimension, multi-vector-at-a-time search. Together with ADSampling/BSA pruning, PDX beats SIMD-optimized horizontal layouts and introduces PDX-BOND, a preprocessing-free pruning strategy for frequent updates. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 7314
Venue: SIGMOD
Year: 2025
Pagerank: 5.559007e-05
Overall Rank: 7,720 | 47.04%
DOI: 10.1145/3725333

Incoming Non-self Citations Over Time

Authors

1. Leonardo Kuffo (Centrum Wiskunde & Informatica)
2. Elena Krippner (Centrum Wiskunde & Informatica)
3. Peter Boncz (Centrum Wiskunde & Informatica)

BibTeX Citation

@inproceedings{kuffo_sigmod25,
        title = {{PDX: A Data Layout for Vector Similarity Search}},
        author = {Kuffo, Leonardo and Krippner, Elena and Boncz, Peter},
        series = {{SIGMOD} '25},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3725333},
        url = {https://dl.acm.org/doi/10.1145/3725333},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,898	Cracking Vector Search Indexes	2025	VLDB	5.3495662e-05
10,034	HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search	2026	SIGMOD	5.173224e-05
10,336	Accelerating High-Dimensional ANN Search via Skipping Redundant Distance Computations	2026	SIGMOD	5.093636e-05
10,506	This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch!	2026	SIGMOD	5.093636e-05

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.

Rank	Cited Paper	Year	Venue	Pagerank
14	MonetDB/X100: Hyper-Pipelining Query Execution	2005	CIDR	0.0006312782
49	Weaving Relations for Cache Performance	2001	VLDB	0.00043781096
93	Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph	2019	VLDB	0.00034701237
103	DuckDB: an Embeddable Analytical Database	2019	SIGMOD	0.00034161428
286	Milvus: A Purpose-Built Vector Data Management System	2021	SIGMOD	0.00022357911
398	A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search	2021	VLDB	0.00019194947
1,357	RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search	2024	SIGMOD	0.00011043994
1,735	High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations	2023	SIGMOD	9.9004924e-05
1,760	Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment	2024	SIGMOD	9.8157819e-05
2,519	Similarity search in the blink of an eye with compressed indices	2023	VLDB	8.4741476e-05
3,269	ALP: Adaptive Lossless floating-Point Compression	2023	SIGMOD	7.5809516e-05
3,363	Efficient k-NN Search on Vertically Decomposed Data	2002	SIGMOD	7.4808966e-05
3,592	The FastLanes Compression Layout: Decoding >100 Billion Integers per Second with Scalar Code	2023	VLDB	7.2774889e-05
4,457	Analyzing and Comparing Lakehouse Storage Systems	2023	CIDR	6.6913393e-05
6,277	Rethinking MIMD-SIMD Interplay for Analytical Query Processing in In-Memory Database Engines	2025	CIDR	5.9288764e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	13,652	Universal Indexing of Arbitrary Similarity Models	2013	VLDB
2	10,447	Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph	2026	SIGMOD
3	21	Similarity Search in High Dimensions via Hashing	1999	VLDB
4	9,964	DIDS: Double Indices and Double Summarizations for Fast Similarity Search	2024	VLDB
5	797	Dimensionality Reduction for Similarity Searching in Dynamic Databases	1998	SIGMOD
6	1,722	Indexable PLA for Efficient Similarity Search	2007	VLDB
7	2,519	Similarity search in the blink of an eye with compressed indices	2023	VLDB
8	8,655	A Non-Linear Dimensionality-Reduction Technique for Fast Similarity Search in Large Databases	2006	SIGMOD
9	46	A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces	1998	VLDB
10	10,227	Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search	2026	SIGMOD