PairDistill: Pairwise Relevance Distillation for Dense Retrieval

• URL: http://arxiv.org/abs/2410.01383v1
• Date: Wed, 2 Oct 2024 09:51:42 GMT
• Title: PairDistill: Pairwise Relevance Distillation for Dense Retrieval
• Authors: Chao-Wei Huang, Yun-Nung Chen,
• Abstract summary: This paper introduces Pairwise Relevance Distillation (PairDistill) to leverage pairwise reranking. It offers fine-grained distinctions between similarly relevant documents to enrich the training of dense retrieval models. Our experiments demonstrate that PairDistill outperforms existing methods, achieving new state-of-the-art results across multiple benchmarks.
• Score: 35.067998820937284
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Effective information retrieval (IR) from vast datasets relies on advanced techniques to extract relevant information in response to queries. Recent advancements in dense retrieval have showcased remarkable efficacy compared to traditional sparse retrieval methods. To further enhance retrieval performance, knowledge distillation techniques, often leveraging robust cross-encoder rerankers, have been extensively explored. However, existing approaches primarily distill knowledge from pointwise rerankers, which assign absolute relevance scores to documents, thus facing challenges related to inconsistent comparisons. This paper introduces Pairwise Relevance Distillation (PairDistill) to leverage pairwise reranking, offering fine-grained distinctions between similarly relevant documents to enrich the training of dense retrieval models. Our experiments demonstrate that PairDistill outperforms existing methods, achieving new state-of-the-art results across multiple benchmarks. This highlights the potential of PairDistill in advancing dense retrieval techniques effectively. Our source code and trained models are released at https://github.com/MiuLab/PairDistill

Related papers

• Efficient Retrieval with Learned Similarities [2.729516456192901]
  State-of-the-art retrieval algorithms have migrated to learned similarities. We show that Mixture-of-Logits (MoL) is a universal approximator, and can express all learned similarity functions. MoL sets new state-of-the-art results on recommendation retrieval tasks, and our approximate top-k retrieval with learned similarities outperforms baselines by up to two orders of magnitude in latency.
  arXiv  Detail & Related papers  (2024-07-22T08:19:34Z)
• 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)
• Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matching [7.908244841289913]
  The expenses involved in training state-of-the-art deep hashing retrieval models have witnessed an increase. The state-of-the-art dataset distillation methods can not expand to all deep hashing retrieval methods. We propose an efficient condensation framework that addresses these limitations by matching the feature-embedding between synthetic set and real set.
  arXiv  Detail & Related papers  (2023-05-29T13:23:55Z)
• Fine-Grained Distillation for Long Document Retrieval [86.39802110609062]
  Long document retrieval aims to fetch query-relevant documents from a large-scale collection. Knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. We propose a new learning framework, fine-grained distillation (FGD), for long-document retrievers.
  arXiv  Detail & Related papers  (2022-12-20T17:00:36Z)
• Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation [77.34726150561087]
  This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest new data distillation techniques based on generative teaching networks, gradient matching, and the Implicit Function Theorem.
  arXiv  Detail & Related papers  (2022-03-16T11:45:32Z)
• PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval [87.68667887072324]
  We propose a novel approach that leverages query-centric and PAssage-centric sImilarity Relations (called PAIR) for dense passage retrieval. To implement our approach, we make three major technical contributions by introducing formal formulations of the two kinds of similarity relations. Our approach significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions datasets.
  arXiv  Detail & Related papers  (2021-08-13T02:07:43Z)
• Combining Feature and Instance Attribution to Detect Artifacts [62.63504976810927]
  We propose methods to facilitate identification of training data artifacts. We show that this proposed training-feature attribution approach can be used to uncover artifacts in training data. We execute a small user study to evaluate whether these methods are useful to NLP researchers in practice.
  arXiv  Detail & Related papers  (2021-07-01T09:26:13Z)
• Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator [62.26981903551382]
  Variational auto-encoders (VAEs) with binary latent variables provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. This new semantic hashing framework achieves superior performance compared to the state-of-the-arts.
  arXiv  Detail & Related papers  (2020-05-21T06:11:33Z)

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.