Faster Learned Sparse Retrieval with Block-Max Pruning

• URL: http://arxiv.org/abs/2405.01117v1
• Date: Thu, 02 May 2024 09:26:30 GMT
• Title: Faster Learned Sparse Retrieval with Block-Max Pruning
• Authors: Antonio Mallia, Torten Suel, Nicola Tonellotto,
• Abstract summary: This paper introduces Block-Max Pruning (BMP), an innovative dynamic pruning strategy tailored for indexes arising in learned sparse retrieval environments. BMP substantially outperforms existing dynamic pruning strategies, offering unparalleled efficiency in safe retrieval contexts.
• Score: 11.080810272211906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learned sparse retrieval systems aim to combine the effectiveness of contextualized language models with the scalability of conventional data structures such as inverted indexes. Nevertheless, the indexes generated by these systems exhibit significant deviations from the ones that use traditional retrieval models, leading to a discrepancy in the performance of existing query optimizations that were specifically developed for traditional structures. These disparities arise from structural variations in query and document statistics, including sub-word tokenization, leading to longer queries, smaller vocabularies, and different score distributions within posting lists. This paper introduces Block-Max Pruning (BMP), an innovative dynamic pruning strategy tailored for indexes arising in learned sparse retrieval environments. BMP employs a block filtering mechanism to divide the document space into small, consecutive document ranges, which are then aggregated and sorted on the fly, and fully processed only as necessary, guided by a defined safe early termination criterion or based on approximate retrieval requirements. Through rigorous experimentation, we show that BMP substantially outperforms existing dynamic pruning strategies, offering unparalleled efficiency in safe retrieval contexts and improved tradeoffs between precision and efficiency in approximate retrieval tasks.

Related papers

• Constrained Auto-Regressive Decoding Constrains Generative Retrieval [71.71161220261655]
  Generative retrieval seeks to replace traditional search index data structures with a single large-scale neural network. In this paper, we examine the inherent limitations of constrained auto-regressive generation from two essential perspectives: constraints and beam search.
  arXiv  Detail & Related papers  (2025-04-14T06:54:49Z)
• GENIUS: A Generative Framework for Universal Multimodal Search [26.494338650656594]
  This paper proposes GENIUS, a universal generative retrieval framework supporting diverse tasks across multiple modalities and domains. At its core, GENIUS introduces modality-decoupled semantic quantization, transforming multimodal data into discrete IDs encoding both modality and semantics. To enhance generalization, we propose a query augmentation that interpolates between a query and its target, allowing GENIUS to adapt to varied query forms.
  arXiv  Detail & Related papers  (2025-03-25T17:32:31Z)
• Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search [65.53881294642451]
  Deliberate Thinking based Dense Retriever (DEBATER) DEBATER enhances recent dense retrievers by enabling them to learn more effective document representations through a step-by-step thinking process. Experimental results show that DEBATER significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• Unifying Generative and Dense Retrieval for Sequential Recommendation [37.402860622707244]
  We propose LIGER, a hybrid model that combines the strengths of sequential dense retrieval and generative retrieval. LIGER integrates sequential dense retrieval into generative retrieval, mitigating performance differences and enhancing cold-start item recommendation. This hybrid approach provides insights into the trade-offs between these approaches and demonstrates improvements in efficiency and effectiveness for recommendation systems in small-scale benchmarks.
  arXiv  Detail & Related papers  (2024-11-27T23:36:59Z)
• Retrieval with Learned Similarities [2.729516456192901]
  State-of-the-art retrieval algorithms have migrated to learned similarities. We show that Mixture-of-Logits (MoL) can be realized empirically to achieve superior performance on diverse retrieval scenarios.
  arXiv  Detail & Related papers  (2024-07-22T08:19:34Z)
• ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  We propose a pioneering generAtive Cross-modal rEtrieval framework (ACE) for end-to-end cross-modal retrieval. ACE achieves state-of-the-art performance in cross-modal retrieval and outperforms the strong baselines on Recall@1 by 15.27% on average.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• User Intent Recognition and Semantic Cache Optimization-Based Query Processing Framework using CFLIS and MGR-LAU [0.0]
  This work analyzed the informational, navigational, and transactional-based intents in queries for enhanced QP. For efficient QP, the data is structured using Epanechnikov Kernel-Ordering Points To Identify the Clustering Structure (EK-OPTICS) The extracted features, detected intents and structured data are inputted to the Multi-head Gated Recurrent Learnable Attention Unit (MGR-LAU)
  arXiv  Detail & Related papers  (2024-06-06T20:28:05Z)
• 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)
• Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations [8.796275989527054]
  We propose a novel organization of the inverted index that enables fast retrieval over learned sparse embeddings. Our approach organizes inverted lists into geometrically-cohesive blocks, each equipped with a summary vector. Our results indicate that Seismic is one to two orders of magnitude faster than state-of-the-art inverted index-based solutions.
  arXiv  Detail & Related papers  (2024-04-29T15:49:27Z)
• 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)
• Augmented Embeddings for Custom Retrievals [13.773007276544913]
  We introduce Adapted Dense Retrieval, a mechanism to transform embeddings to enable improved task-specific, heterogeneous and strict retrieval. Dense Retrieval works by learning a low-rank residual adaptation of the pretrained black-box embedding.
  arXiv  Detail & Related papers  (2023-10-09T03:29:35Z)
• How Does Generative Retrieval Scale to Millions of Passages? [68.98628807288972]
  We conduct the first empirical study of generative retrieval techniques across various corpus scales. We scale generative retrieval to millions of passages with a corpus of 8.8M passages and evaluating model sizes up to 11B parameters. While generative retrieval is competitive with state-of-the-art dual encoders on small corpora, scaling to millions of passages remains an important and unsolved challenge.
  arXiv  Detail & Related papers  (2023-05-19T17:33:38Z)
• 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)
• A Learned Index for Exact Similarity Search in Metric Spaces [25.330353637669386]
  LIMS is proposed to use data clustering and pivot-based data transformation techniques to build learned indexes. Machine learning models are developed to approximate the position of each data record on the disk. Extensive experiments on real-world and synthetic datasets demonstrate the superiority of LIMS compared with traditional indexes.
  arXiv  Detail & Related papers  (2022-04-21T11:24:55Z)
• 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.