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)
Incoming Non-self Citations Over Time
Authors
- 1. Leonardo Kuffo
- 2. Elena Krippner
- 3. Peter Boncz
Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,879 | HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search | 2026 | SIGMOD | 4.2643674e-05 |
| 10,042 | Accelerating High-Dimensional ANN Search via Skipping Redundant Distance Computations | 2026 | SIGMOD | 4.1945683e-05 |
| 10,217 | 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 | 4.1945683e-05 |
| 10,711 | Cracking Vector Search Indexes | 2025 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next
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.
Previous
Page 1 / 1
Next