Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

• URL: http://arxiv.org/abs/2605.01965v1
• Date: Sun, 03 May 2026 16:51:41 GMT
• Title: Retrieval with Multiple Query Vectors through Anomalous Pattern Detection
• Abstract summary: A classical vector retrieval problem typically considers a emphsingle query embedding vector as input and retrieves the most similar embedding vectors from a vector database.<n>We propose a retrieval method that considers multiple query vectors simultaneously and retrieves the most relevant vectors from the database using concepts from anomalous pattern detection.
• Score: 3.5501866628044563
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A classical vector retrieval problem typically considers a \emph{single} query embedding vector as input and retrieves the most similar embedding vectors from a vector database. However, complex reasoning and retrieval tasks frequently require \emph{multiple query vectors}, rather than a single one. In this work, we propose a retrieval method that considers multiple query vectors simultaneously and retrieves the most relevant vectors from the database using concepts from anomalous pattern detection. Specifically, our approach leverages a set of query vectors $Q$ (with $|Q|\geq 1$), and identifies the subset of vector dimensions within $Q$ that standout (anomalous) from the rest of dimensions. Next, we scan the vector database to retrieve the set of vectors that are also anomalous across the previously identified vector dimensions and return them as our retrieved set of vectors. We validate our approach on two image datasets, a text dataset, and a tabular dataset. Overall, we observe that, across most datasets, larger query sets lead to improved retrieval performance. The improvement is most pronounced when increasing the query sets from 1 to 8, while the gains become smaller beyond that.

Related papers

• Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval [45.166788898665665]
  We develop a new retriever architecture, emphAutoregressive emphMulti-emphEmbedding emphRetriever (AMER)<n>Our model autoregressively generates multiple query vectors, and all the predicted query vectors are used to retrieve documents from the corpus.<n>AMER presents 4 and 21% relative gains over single-embedding baselines on two datasets we evaluate on.
  arXiv  Detail & Related papers  (2025-11-04T17:57:20Z)
• Generative Retrieval as Multi-Vector Dense Retrieval [71.75503049199897]
  Generative retrieval generates identifiers of relevant documents in an end-to-end manner. Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval. We show that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document.
  arXiv  Detail & Related papers  (2024-03-31T13:29:43Z)
• 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)
• Vector search with small radiuses [10.880913075221361]
  This paper focuses on the common case where a hard decision needs to be taken depending on the vector retrieval results. We show that the value of a range search result can be modeled rigorously based on the query-to-vector distance. This yields a metric for range search, RSM, that is both principled and easy to compute without running an end-to-end evaluation.
  arXiv  Detail & Related papers  (2024-03-16T00:34:25Z)
• The Faiss library [48.38564920607163]
  Faiss is a toolkit of indexing methods and related primitives used to search, cluster, compress and transform vectors.<n>This paper describes the trade-off space of vector search and the design principles of Faiss in terms of structure, approach to optimization and interfacing.
  arXiv  Detail & Related papers  (2024-01-16T11:12:36Z)
• 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)
• Efficient Set of Vectors Search [2.741266294612776]
  We present approximate search algorithms for the general case. The underlying idea in these algorithms is encoding a set of vectors via a "long" single vector.
  arXiv  Detail & Related papers  (2021-07-14T16:22:20Z)
• Support Recovery of Sparse Signals from a Mixture of Linear Measurements [48.556633593447465]
  Recovery of support of a sparse vector from simple measurements is a widely studied problem. We consider generalizations of this problem: mixtures of linear regressions, and mixtures of linear classifiers. We provide algorithms that use a number of measurements in $k, log n$ and quasi-polynomial in $ell$ to recover the support of all the unknown vectors in the mixture.
  arXiv  Detail & Related papers  (2021-06-10T17:48:13Z)
• Recovery of sparse linear classifiers from mixture of responses [42.228977798395846]
  We show how to learn a collection of hyperplanes from a sequence of binary responses. Each response is a result of querying with a vector and indicates the side of a randomly chosen hyperplane from the collection the query vector belongs to.
  arXiv  Detail & Related papers  (2020-10-22T22:03:53Z)
• Vector-Matrix-Vector Queries for Solving Linear Algebra, Statistics, and Graph Problems [58.83118651518438]
  We consider the general problem of learning about a matrix through vector-matrix-vector queries. These queries provide the value of $boldsymbolumathrmTboldsymbolMboldsymbolv$ over a fixed field. We provide new upper and lower bounds for a wide variety of problems, spanning linear algebra, statistics, and graphs.
  arXiv  Detail & Related papers  (2020-06-24T19:33:49Z)

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.