Experimental Analysis of Large-scale Learnable Vector Storage Compression

• URL: http://arxiv.org/abs/2311.15578v2
• Date: Tue, 13 Feb 2024 09:38:44 GMT
• Title: Experimental Analysis of Large-scale Learnable Vector Storage Compression
• Authors: Hailin Zhang, Penghao Zhao, Xupeng Miao, Yingxia Shao, Zirui Liu, Tong Yang, Bin Cui
• Abstract summary: Learnable embedding vector is one of the most important applications in machine learning. The high dimensionality of sparse data in recommendation tasks and the huge volume of corpus in retrieval-related tasks lead to a large memory consumption of the embedding table. Recent research has proposed various methods to compress the embeddings at the cost of a slight decrease in model quality or the introduction of other overheads.
• Score: 42.52474894105165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learnable embedding vector is one of the most important applications in machine learning, and is widely used in various database-related domains. However, the high dimensionality of sparse data in recommendation tasks and the huge volume of corpus in retrieval-related tasks lead to a large memory consumption of the embedding table, which poses a great challenge to the training and deployment of models. Recent research has proposed various methods to compress the embeddings at the cost of a slight decrease in model quality or the introduction of other overheads. Nevertheless, the relative performance of these methods remains unclear. Existing experimental comparisons only cover a subset of these methods and focus on limited metrics. In this paper, we perform a comprehensive comparative analysis and experimental evaluation of embedding compression. We introduce a new taxonomy that categorizes these techniques based on their characteristics and methodologies, and further develop a modular benchmarking framework that integrates 14 representative methods. Under a uniform test environment, our benchmark fairly evaluates each approach, presents their strengths and weaknesses under different memory budgets, and recommends the best method based on the use case. In addition to providing useful guidelines, our study also uncovers the limitations of current methods and suggests potential directions for future research.

Related papers

• Preview-based Category Contrastive Learning for Knowledge Distillation [53.551002781828146]
  We propose a novel preview-based category contrastive learning method for knowledge distillation (PCKD) It first distills the structural knowledge of both instance-level feature correspondence and the relation between instance features and category centers. It can explicitly optimize the category representation and explore the distinct correlation between representations of instances and categories.
  arXiv  Detail & Related papers  (2024-10-18T03:31:00Z)
• Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric [99.19559537966538]
  DML aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. To maintain the structure of embedding space and avoid feature collapse, we propose a novel loss function called Anti-Collapse Loss. Comprehensive experiments on benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-03T13:44:20Z)
• When is an Embedding Model More Promising than Another? [33.540506562970776]
  Embedders play a central role in machine learning, projecting any object into numerical representations that can be leveraged to perform various downstream tasks. The evaluation of embedding models typically depends on domain-specific empirical approaches. We present a unified approach to evaluate embedders, drawing upon the concepts of sufficiency and informativeness.
  arXiv  Detail & Related papers  (2024-06-11T18:13:46Z)
• A Large-Scale Neutral Comparison Study of Survival Models on Low-Dimensional Data [7.199059106376138]
  This work presents the first large-scale neutral benchmark experiment focused on single-event, right-censored, low-dimensional survival data. We benchmark 18 models, ranging from classical statistical approaches to many common machine learning methods, on 32 publicly available datasets.
  arXiv  Detail & Related papers  (2024-06-06T14:13:38Z)
• Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense Encoders [63.28408887247742]
  We study whether training procedures can be improved to yield better generalization capabilities in the resulting models. We recommend a simple recipe for training dense encoders: Train on MSMARCO with parameter-efficient methods, such as LoRA, and opt for using in-batch negatives unless given well-constructed hard negatives.
  arXiv  Detail & Related papers  (2023-11-16T10:42:58Z)
• Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluation [64.0476282000118]
  Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. It is currently difficult to compare the performance of these VCE methods as the evaluation procedures largely vary and often boil down to visual inspection of individual examples and small scale user studies. We propose a framework for systematic, quantitative evaluation of the VCE methods and a minimal set of metrics to be used.
  arXiv  Detail & Related papers  (2023-08-11T12:22:37Z)
• On the role of benchmarking data sets and simulations in method comparison studies [0.0]
  This paper investigates differences and similarities between simulation studies and benchmarking studies. We borrow ideas from different contexts such as mixed methods research and Clinical Scenario Evaluation.
  arXiv  Detail & Related papers  (2022-08-02T13:47:53Z)
• A Typology for Exploring the Mitigation of Shortcut Behavior [29.38025128165229]
  We provide a unification of various XIL methods into a single typology by establishing a common set of basic modules. In our evaluations, all methods prove to revise a model successfully. However, we found remarkable differences in individual benchmark tasks, revealing valuable application-relevant aspects.
  arXiv  Detail & Related papers  (2022-03-04T14:16:50Z)
• Compressing Large Sample Data for Discriminant Analysis [78.12073412066698]
  We consider the computational issues due to large sample size within the discriminant analysis framework. We propose a new compression approach for reducing the number of training samples for linear and quadratic discriminant analysis.
  arXiv  Detail & Related papers  (2020-05-08T05:09:08Z)

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.