SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training

• URL: http://arxiv.org/abs/2407.06654v1
• Date: Tue, 9 Jul 2024 08:26:39 GMT
• Title: SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training
• Authors: Nan He, Weichen Xiong, Hanwen Liu, Yi Liao, Lei Ding, Kai Zhang, Guohua Tang, Xiao Han, Wei Yang,
• Abstract summary: We propose a soft deduplication method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness. Central to our approach is the concept of "data commonness", a metric we introduce to quantify the degree of duplication. Empirical analysis shows that this method significantly improves training efficiency, achieving comparable perplexity scores with at least a 26% reduction in required training steps.
• Score: 12.745160748376794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication. To address this, we propose a soft deduplication method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness. Central to our approach is the concept of "data commonness", a metric we introduce to quantify the degree of duplication by measuring the occurrence probabilities of samples using an n-gram model. Empirical analysis shows that this method significantly improves training efficiency, achieving comparable perplexity scores with at least a 26% reduction in required training steps. Additionally, it enhances average few-shot downstream accuracy by 1.77% when trained for an equivalent duration. Importantly, this approach consistently improves performance, even on rigorously deduplicated datasets, indicating its potential to complement existing methods and become a standard pre-training process for LLMs.

Related papers

• Optimizing Pretraining Data Mixtures with LLM-Estimated Utility [52.08428597962423]
  Large Language Models improve with increasing amounts of high-quality training data. We find token-counts outperform manual and learned mixes, indicating that simple approaches for dataset size and diversity are surprisingly effective. We propose two complementary approaches: UtiliMax, which extends token-based $200s by incorporating utility estimates from reduced-scale ablations, achieving up to a 10.6x speedup over manual baselines; and Model Estimated Data Utility (MEDU), which leverages LLMs to estimate data utility from small samples, matching ablation-based performance while reducing computational requirements by $simx.
  arXiv  Detail & Related papers  (2025-01-20T21:10:22Z)
• Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification [13.732596789612362]
  This work is the first to explore the feasibility of data pruning methods applied to object re-identification tasks. By fully leveraging the logit history during training, our approach offers a more accurate and comprehensive metric for quantifying sample importance. Our approach is highly efficient, reducing the cost of importance score estimation by 10 times compared to existing methods.
  arXiv  Detail & Related papers  (2024-12-13T12:27:47Z)
• Fine-tuning can Help Detect Pretraining Data from Large Language Models [7.7209640786782385]
  Current methods differentiate members and non-members by designing scoring functions, like Perplexity and Min-k%. We introduce a novel and effective method termed Fine-tuned Score Deviation (FSD), which improves the performance of current scoring functions for pretraining data detection.
  arXiv  Detail & Related papers  (2024-10-09T15:36:42Z)
• Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization [30.738229850748137]
  MolPeg is a Molecular data Pruning framework for enhanced Generalization. It focuses on the source-free data pruning scenario, where data pruning is applied with pretrained models. It consistently outperforms existing DP methods across four downstream tasks.
  arXiv  Detail & Related papers  (2024-09-02T09:06:04Z)
• Incremental Self-training for Semi-supervised Learning [56.57057576885672]
  IST is simple yet effective and fits existing self-training-based semi-supervised learning methods. We verify the proposed IST on five datasets and two types of backbone, effectively improving the recognition accuracy and learning speed.
  arXiv  Detail & Related papers  (2024-04-14T05:02:00Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• How to Train Data-Efficient LLMs [56.41105687693619]
  We study data-efficient approaches for pre-training language models (LLMs) We find that Ask-LLM and Density sampling are the best methods in their respective categories. In our comparison of 19 samplers, involving hundreds of evaluation tasks and pre-training runs, we find that Ask-LLM and Density are the best methods in their respective categories.
  arXiv  Detail & Related papers  (2024-02-15T02:27:57Z)
• Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution [62.71425232332837]
  We show that training amortized models with noisy labels is inexpensive and surprisingly effective. This approach significantly accelerates several feature attribution and data valuation methods, often yielding an order of magnitude speedup over existing approaches.
  arXiv  Detail & Related papers  (2024-01-29T03:42:37Z)
• Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation for Time Series [45.76310830281876]
  We propose Quantile Sub-Ensembles, a novel method to estimate uncertainty with ensemble of quantile-regression-based task networks. Our method not only produces accurate imputations that is robust to high missing rates, but also is computationally efficient due to the fast training of its non-generative model.
  arXiv  Detail & Related papers  (2023-12-03T05:52:30Z)
• Improved Distribution Matching for Dataset Condensation [91.55972945798531]
  We propose a novel dataset condensation method based on distribution matching. Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
  arXiv  Detail & Related papers  (2023-07-19T04:07:33Z)
• A Data-Centric Approach for Improving Adversarial Training Through the Lens of Out-of-Distribution Detection [0.4893345190925178]
  We propose detecting and removing hard samples directly from the training procedure rather than applying complicated algorithms to mitigate their effects. Our results on SVHN and CIFAR-10 datasets show the effectiveness of this method in improving the adversarial training without adding too much computational cost.
  arXiv  Detail & Related papers  (2023-01-25T08:13:50Z)

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.