PDX: A Data Layout for Vector Similarity Search

• URL: http://arxiv.org/abs/2503.04422v1
• Date: Thu, 06 Mar 2025 13:31:16 GMT
• Title: PDX: A Data Layout for Vector Similarity Search
• Authors: Leonardo Kuffo, Elena Krippner, Peter Boncz,
• Abstract summary: Partition Across Dimensions (PDX) is a data layout for vectors that stores multiple vectors in one block, using a vertical layout for the dimensions.<n>PDX beats SIMD-optimized distance kernels on standard horizontal vector storage (avg 40% faster)<n>We introduce PDX-BOND, an even more flexible dimension-pruning strategy, with good performance on exact search and reasonable performance on approximate search.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose Partition Dimensions Across (PDX), a data layout for vectors (e.g., embeddings) that, similar to PAX [6], stores multiple vectors in one block, using a vertical layout for the dimensions (Figure 1). PDX accelerates exact and approximate similarity search thanks to its dimension-by-dimension search strategy that operates on multiple-vectors-at-a-time in tight loops. It beats SIMD-optimized distance kernels on standard horizontal vector storage (avg 40% faster), only relying on scalar code that gets auto-vectorized. We combined the PDX layout with recent dimension-pruning algorithms ADSampling [19] and BSA [52] that accelerate approximate vector search. We found that these algorithms on the horizontal vector layout can lose to SIMD-optimized linear scans, even if they are SIMD-optimized. However, when used on PDX, their benefit is restored to 2-7x. We find that search on PDX is especially fast if a limited number of dimensions has to be scanned fully, which is what the dimension-pruning approaches do. We finally introduce PDX-BOND, an even more flexible dimension-pruning strategy, with good performance on exact search and reasonable performance on approximate search. Unlike previous pruning algorithms, it can work on vector data "as-is" without preprocessing; making it attractive for vector databases with frequent updates.

Related papers

• Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search [11.938555573590964]
  Lossy compression has been applied extensively to reduce the size of indexes.<n>For inverted file and graph-based indices, auxiliary data such as vector ids and links can represent most of the storage cost.<n>We show that for some datasets, these methods can also compress the quantized vector codes losslessly.
  arXiv  Detail & Related papers  (2025-01-16T20:45:11Z)
• GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reduction [1.1599570446840546]
  Cross-modal retrieval (e.g., where a text query is used to find images) is gaining momentum rapidly. It is challenging to achieve high accuracy as the queries often have different statistical distributions than the database vectors. We present new linear and nonlinear methods for dimensionality reduction to accelerate high-dimensional vector search.
  arXiv  Detail & Related papers  (2024-10-14T21:14:27Z)
• Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes? [62.57689536630933]
  We provide experimental results on the BEIR dataset using the open-source Lucene search library. Our results provide guidance for today's search practitioner in understanding the design space of dense and sparse retrievers.
  arXiv  Detail & Related papers  (2024-09-10T12:46:23Z)
• MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings [15.275864151890511]
  We introduce MUVERA (MUlti-VEctor Retrieval Algorithm), a retrieval mechanism which reduces multi-vector search to single-vector similarity search. MUVERA achieves consistently good end-to-end recall and latency across a diverse set of the BEIR retrieval datasets.
  arXiv  Detail & Related papers  (2024-05-29T20:40:20Z)
• Efficient Data Access Paths for Mixed Vector-Relational Search [8.80592433569832]
  Machine learning and the adoption of data processing methods using vector embeddings sparked a great interest in creating systems for vector data management. While the predominant approach of vector data management is to use specialized index structures for fast search over the entirety of the vector embeddings, once combined with other (meta)data, the search queries can also become selective on relational attributes. As using vector indexes differs from traditional relational data access, we revisit and analyze alternative access paths for efficient mixed vector-relational search.
  arXiv  Detail & Related papers  (2024-03-23T11:34:17Z)
• LeanVec: Searching vectors faster by making them fit [1.0863382547662974]
  We present LeanVec, a framework that combines linear dimensionality reduction with vector quantization to accelerate similarity search on high-dimensional vectors. We show that LeanVec produces state-of-the-art results, with up to 3.7x improvement in search throughput and up to 4.9x faster index build time.
  arXiv  Detail & Related papers  (2023-12-26T21:14:59Z)
• Linearized Wasserstein dimensionality reduction with approximation guarantees [65.16758672591365]
  LOT Wassmap is a computationally feasible algorithm to uncover low-dimensional structures in the Wasserstein space. We show that LOT Wassmap attains correct embeddings and that the quality improves with increased sample size. We also show how LOT Wassmap significantly reduces the computational cost when compared to algorithms that depend on pairwise distance computations.
  arXiv  Detail & Related papers  (2023-02-14T22:12:16Z)
• CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval [72.90850213615427]
  Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers. These methods are orders of magnitude slower and need much more space to store their indices compared to their single-vector counterparts. We propose conditional token interaction via dynamic lexical routing, namely CITADEL, for efficient and effective multi-vector retrieval.
  arXiv  Detail & Related papers  (2022-11-18T18:27:35Z)
• Rapid Person Re-Identification via Sub-space Consistency Regularization [51.76876061721556]
  Person Re-Identification (ReID) matches pedestrians across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance computation. We propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by 0.25$ times.
  arXiv  Detail & Related papers  (2022-07-13T02:44:05Z)
• Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization [59.87663954467815]
  Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer. In this paper, leveraging a recent linear algebraic theorem called Gershgorin disc perfect alignment (GDPA), we unroll a projection-free algorithm for semi-definite programming relaxation (SDR) of a binary graph. Experimental results show that our unrolled network outperformed pure model-based graph classifiers, and achieved comparable performance to pure data-driven networks but using far fewer parameters.
  arXiv  Detail & Related papers  (2021-09-10T07:01:15Z)
• The Case for Learned Spatial Indexes [62.88514422115702]
  We use techniques proposed from a state-of-the art learned multi-dimensional index structure (namely, Flood) to answer spatial range queries. We show that (i) machine learned search within a partition is faster by 11.79% to 39.51% than binary search when using filtering on one dimension. We also refine using machine learned indexes is 1.23x to 1.83x times faster than closest competitor which filters on two dimensions.
  arXiv  Detail & Related papers  (2020-08-24T12:09:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.