On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation

• URL: http://arxiv.org/abs/2510.00434v1
• Date: Wed, 01 Oct 2025 02:26:52 GMT
• Title: On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
• Abstract summary: We introduce SADA, a Sample-Aware Dynamic Augmentation that performs on-the-fly adjustment of augmentation strengths based on each sample's evolving influence on model optimization.<n>Our method is lightweight, which does not require auxiliary models or policy tuning. It can be seamlessly integrated into existing training pipelines as a plug-and-play module.
• Score: 21.267525672022046
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data augmentation has been widely employed to improve the generalization of deep neural networks. Most existing methods apply fixed or random transformations. However, we find that sample difficulty evolves along with the model's generalization capabilities in dynamic training environments. As a result, applying uniform or stochastic augmentations, without accounting for such dynamics, can lead to a mismatch between augmented data and the model's evolving training needs, ultimately degrading training effectiveness. To address this, we introduce SADA, a Sample-Aware Dynamic Augmentation that performs on-the-fly adjustment of augmentation strengths based on each sample's evolving influence on model optimization. Specifically, we estimate each sample's influence by projecting its gradient onto the accumulated model update direction and computing the temporal variance within a local training window. Samples with low variance, indicating stable and consistent influence, are augmented more strongly to emphasize diversity, while unstable samples receive milder transformations to preserve semantic fidelity and stabilize learning. Our method is lightweight, which does not require auxiliary models or policy tuning. It can be seamlessly integrated into existing training pipelines as a plug-and-play module. Experiments across various benchmark datasets and model architectures show consistent improvements of SADA, including +7.3\% on fine-grained tasks and +4.3\% on long-tailed datasets, highlighting the method's effectiveness and practicality.

Related papers

• Data Attribution in Large Language Models via Bidirectional Gradient Optimization [35.61634772862795]
  Large Language Models (LLMs) are increasingly deployed across diverse applications.<n>understanding which training data most influenced a model's output remains a fundamental open problem.<n>We address this challenge by expanding upon the inverse formulation: How would training data be affected if the model had seen the generated output during training?<n>Our method perturbs the base model using bidirectional gradient optimization (gradient ascent and descent) on a generated text sample and measures the resulting change in loss across training samples.
  arXiv  Detail & Related papers  (2026-06-03T14:21:53Z)
• Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications [0.9174244628582179]
  We propose a novel algorithm that modifies the gradients returned by training examples, specifically, scaling down the gradients of correctly classified examples using a dynamic scaler.<n>Experiments on a variety of benchmark datasets, spanning multiple tasks and large pretrained models, demonstrate that our method consistently reduces performance variance and surpasses the accuracy of existing approaches.
  arXiv  Detail & Related papers  (2026-04-30T15:16:00Z)
• Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks [10.269961654607108]
  Deep neural networks are typically trained by uniformly sampling large datasets across epochs.<n>Recent work shows that progressively reducing the amount of training data can improve efficiency and generalization.<n>We propose Adaptive Data Dropout, a framework that dynamically adjusts the subset of training data based on performance feedback.
  arXiv  Detail & Related papers  (2026-04-14T16:41:33Z)
• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Feasible Learning [78.6167929413604]
  We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample.<n>Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
  arXiv  Detail & Related papers  (2025-01-24T20:39:38Z)
• AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation [12.697608744311122]
  AdaAugment is a tuning-free adaptive augmentation method for deep models.<n>It adapts augmentation magnitudes based on real-time feedback from the target network.<n>Experiments show it consistently outperforms other state-of-the-art DA methods.
  arXiv  Detail & Related papers  (2024-05-19T06:54:03Z)
• Boosting Model Resilience via Implicit Adversarial Data Augmentation [20.768174896574916]
  We propose to augment the deep features of samples by incorporating adversarial and anti-adversarial perturbation distributions. We then theoretically reveal that our augmentation process approximates the optimization of a surrogate loss function. We conduct extensive experiments across four common biased learning scenarios.
  arXiv  Detail & Related papers  (2024-04-25T03:22:48Z)
• Task adaption by biologically inspired stochastic comodulation [8.59194778459436]
  We show that fine-tuning convolutional networks by gain modulation improves on deterministic gain modulation. Our results suggest that comodulation representations can enhance learning efficiency and performance in multi-task learning.
  arXiv  Detail & Related papers  (2023-11-25T15:21:03Z)
• Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation [67.18144414660681]
  We propose a Fast-Slow Test-Time Adaptation (FSTTA) approach for online Vision-and-Language Navigation (VLN) Our method obtains impressive performance gains on four popular benchmarks.
  arXiv  Detail & Related papers  (2023-11-22T07:47:39Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data [93.06336507035486]
  Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
  arXiv  Detail & Related papers  (2022-10-27T02:55:15Z)
• Learning Neural Models for Natural Language Processing in the Face of Distributional Shift [10.990447273771592]
  The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications. It builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. It is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime
  arXiv  Detail & Related papers  (2021-09-03T14:29:20Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Dynamic Scale Training for Object Detection [111.33112051962514]
  We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Experimental results demonstrate the efficacy of our proposed DST towards scale variation handling. It does not introduce inference overhead and could serve as a free lunch for general detection configurations.
  arXiv  Detail & Related papers  (2020-04-26T16:48:17Z)

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.