Early Exit Strategies for Approximate k-NN Search in Dense Retrieval

• URL: http://arxiv.org/abs/2408.04981v1
• Date: Fri, 09 Aug 2024 10:17:07 GMT
• Title: Early Exit Strategies for Approximate k-NN Search in Dense Retrieval
• Authors: Francesco Busolin, Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Salvatore Trani,
• Abstract summary: We build upon state-of-the-art for early exit A-kNN and propose an unsupervised method based on the notion of patience. We show that our techniques improve the A-kNN efficiency with up to 5x speedups while achieving negligible effectiveness losses.
• Score: 10.48678957367324
• License:
• Abstract: Learned dense representations are a popular family of techniques for encoding queries and documents using high-dimensional embeddings, which enable retrieval by performing approximate k nearest-neighbors search (A-kNN). A popular technique for making A-kNN search efficient is based on a two-level index, where the embeddings of documents are clustered offline and, at query processing, a fixed number N of clusters closest to the query is visited exhaustively to compute the result set. In this paper, we build upon state-of-the-art for early exit A-kNN and propose an unsupervised method based on the notion of patience, which can reach competitive effectiveness with large efficiency gains. Moreover, we discuss a cascade approach where we first identify queries that find their nearest neighbor within the closest t << N clusters, and then we decide how many more to visit based on our patience approach or other state-of-the-art strategies. Reproducible experiments employing state-of-the-art dense retrieval models and publicly available resources show that our techniques improve the A-kNN efficiency with up to 5x speedups while achieving negligible effectiveness losses. All the code used is available at https://github.com/francescobusolin/faiss_pEE

Related papers

• CANDY: A Benchmark for Continuous Approximate Nearest Neighbor Search with Dynamic Data Ingestion [8.036012885171166]
  We introduce CANDY, a benchmark tailored for Continuous Approximate Nearest Neighbor Search with Dynamic Data Ingestion. CANDY comprehensively assesses a wide range of AKNN algorithms, integrating advanced optimizations such as machine learning-driven inference. Our evaluations across diverse datasets demonstrate that simpler AKNN baselines often surpass more complex alternatives in terms of recall and latency.
  arXiv  Detail & Related papers  (2024-06-28T04:46:11Z)
• Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders [77.84801537608651]
  Cross-encoder (CE) models which compute similarity by jointly encoding a query-item pair perform better than embedding-based models (dual-encoders) at estimating query-item relevance. We propose a sparse-matrix factorization based method that efficiently computes latent query and item embeddings to approximate CE scores and performs k-NN search with the approximate CE similarity.
  arXiv  Detail & Related papers  (2024-05-06T17:14:34Z)
• PECANN: Parallel Efficient Clustering with Graph-Based Approximate Nearest Neighbor Search [8.15681999722805]
  This paper studies density-based clustering of point sets. It unifies the different variants of density peaks clustering into a single framework, PECANN. We implement five clustering algorithms with PECANN and evaluate them on synthetic and real-world datasets with up to 1.28 million points and up to 1024 dimensions on a 30-core machine with two-way hyper-threading.
  arXiv  Detail & Related papers  (2023-12-06T22:43:50Z)
• Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations [20.944914202453962]
  We study the worst-case performance of graph-based approximate nearest neighbor search algorithms. For DiskANN, we show that its "slow preprocessing" version provably supports approximate nearest neighbor search query. We present a family of instances on which the empirical query time required to achieve a "reasonable" accuracy is linear in instance size.
  arXiv  Detail & Related papers  (2023-10-29T19:25:48Z)
• Lexically-Accelerated Dense Retrieval [29.327878974130055]
  'LADR' (Lexically-Accelerated Dense Retrieval) is a simple-yet-effective approach that improves the efficiency of existing dense retrieval models. LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks.
  arXiv  Detail & Related papers  (2023-07-31T15:44:26Z)
• Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition [77.4863142882136]
  Cross-encoder models are prohibitively expensive for direct k-nearest neighbor (k-NN) search. We propose ADACUR, a method that adaptively, iteratively, and efficiently minimizes the approximation error for the practically important top-k neighbors.
  arXiv  Detail & Related papers  (2023-05-04T17:01:17Z)
• A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph [51.880164098926166]
  Graph-based algorithms have demonstrated state-of-the-art performance in the nearest neighbor search (NN-Search) problem. There exists a practice-to-theory gap in the graph-based NN-Search algorithms. We present theoretical guarantees of solving NN-Search via greedy search on ANN-Graph for low dimensional and dense vectors.
  arXiv  Detail & Related papers  (2023-03-10T21:18:34Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• BR-NS: an Archive-less Approach to Novelty Search [70.13948372218849]
  We discuss an alternative approach to novelty estimation, dubbed Behavior Recognition based Novelty Search (BR-NS) BR-NS does not require an archive, makes no assumption on the metrics that can be defined in the behavior space and does not rely on nearest neighbours search. We conduct experiments to gain insight into its feasibility and dynamics as well as potential advantages over archive-based NS in terms of time complexity.
  arXiv  Detail & Related papers  (2021-04-08T17:31:34Z)
• Leveraging Reinforcement Learning for evaluating Robustness of KNN Search Algorithms [0.0]
  The problem of finding K-nearest neighbors in the given dataset for a given query point has been worked upon since several years. In this paper, we survey some novel K-Nearest Neighbor Search approaches that tackles the problem of Search from the perspectives of computations. In order to evaluate the robustness of a KNNS approach against adversarial points, we propose a generic Reinforcement Learning based framework for the same.
  arXiv  Detail & Related papers  (2021-02-10T16:10:58Z)
• Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering [87.32442219333046]
  We propose a simple and resource-efficient method to pretrain the paragraph encoder. Our method outperforms an existing dense retrieval method that uses 7 times more computational resources for pretraining.
  arXiv  Detail & Related papers  (2020-04-30T18:09:50Z)

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.