Dataset Distillation with Neural Characteristic Function: A Minmax Perspective

• URL: http://arxiv.org/abs/2502.20653v1
• Date: Fri, 28 Feb 2025 02:14:55 GMT
• Title: Dataset Distillation with Neural Characteristic Function: A Minmax Perspective
• Authors: Shaobo Wang, Yicun Yang, Zhiyuan Liu, Chenghao Sun, Xuming Hu, Conghui He, Linfeng Zhang,
• Abstract summary: We reformulate dataset distillation as a minmax optimization problem and introduce Neural Characteristic Function Discrepancy (NCFD)<n>NCFD is a comprehensive and theoretically grounded metric for measuring distributional differences.<n>Our method achieves significant performance gains over state-of-the-art methods on both low- and high-resolution datasets.
• Score: 39.77640775591437
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dataset distillation has emerged as a powerful approach for reducing data requirements in deep learning. Among various methods, distribution matching-based approaches stand out for their balance of computational efficiency and strong performance. However, existing distance metrics used in distribution matching often fail to accurately capture distributional differences, leading to unreliable measures of discrepancy. In this paper, we reformulate dataset distillation as a minmax optimization problem and introduce Neural Characteristic Function Discrepancy (NCFD), a comprehensive and theoretically grounded metric for measuring distributional differences. NCFD leverages the Characteristic Function (CF) to encapsulate full distributional information, employing a neural network to optimize the sampling strategy for the CF's frequency arguments, thereby maximizing the discrepancy to enhance distance estimation. Simultaneously, we minimize the difference between real and synthetic data under this optimized NCFD measure. Our approach, termed Neural Characteristic Function Matching (\mymethod{}), inherently aligns the phase and amplitude of neural features in the complex plane for both real and synthetic data, achieving a balance between realism and diversity in synthetic samples. Experiments demonstrate that our method achieves significant performance gains over state-of-the-art methods on both low- and high-resolution datasets. Notably, we achieve a 20.5\% accuracy boost on ImageSquawk. Our method also reduces GPU memory usage by over 300$\times$ and achieves 20$\times$ faster processing speeds compared to state-of-the-art methods. To the best of our knowledge, this is the first work to achieve lossless compression of CIFAR-100 on a single NVIDIA 2080 Ti GPU using only 2.3 GB of memory.

Related papers

• Dataset Distillation as Pushforward Optimal Quantization [1.039189397779466]
  We propose a simple extension of the state-of-the-art data distillation method D4M, achieving better performance on the ImageNet-1K dataset with trivial additional computation.<n>We demonstrate that when equipped with an encoder-decoder structure, the empirically successful disentangled methods can be reformulated as an optimal quantization problem.<n>In particular, we link existing disentangled dataset distillation methods to the classical optimal quantization and Wasserstein barycenter problems, demonstrating consistency of distilled datasets for diffusion-based generative priors.
  arXiv  Detail & Related papers  (2025-01-13T20:41:52Z)
• Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation [44.03611131165989]
  We propose a novel generative parameterization method dubbed Hierarchical generative Distillation (H-PD) The proposed H-PD achieves a significant performance improvement under various settings with equivalent time consumption. It even surpasses current generative distillation using diffusion models under extreme compression ratios IPC=1 and IPC=10.
  arXiv  Detail & Related papers  (2024-06-09T09:15:54Z)
• Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling [49.215957313126324]
  Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend to produce over-smoothed results, while GAN-based methods easily generate fake details. We propose Boundary-aware Decoupled Flow Networks (BDFlow) to generate realistic and visually pleasing results.
  arXiv  Detail & Related papers  (2024-05-05T14:05:33Z)
• Parallel and Limited Data Voice Conversion Using Stochastic Variational Deep Kernel Learning [2.5782420501870296]
  This paper proposes a voice conversion method that works with limited data. It is based on variational deep kernel learning (SVDKL) It is possible to estimate non-smooth and more complex functions.
  arXiv  Detail & Related papers  (2023-09-08T16:32:47Z)
• Learning Unnormalized Statistical Models via Compositional Optimization [73.30514599338407]
  Noise-contrastive estimation(NCE) has been proposed by formulating the objective as the logistic loss of the real data and the artificial noise. In this paper, we study it a direct approach for optimizing the negative log-likelihood of unnormalized models.
  arXiv  Detail & Related papers  (2023-06-13T01:18:16Z)
• Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization [51.41175648612714]
  We propose a new robust contrastive loss inspired by distributionally robust optimization (DRO) We show that our algorithm automatically learns a suitable $tau$ for each sample. Our method outperforms prior strong baselines on unimodal and bimodal datasets.
  arXiv  Detail & Related papers  (2023-05-19T19:25:56Z)
• Efficient Parametric Approximations of Neural Network Function Space Distance [6.117371161379209]
  It is often useful to compactly summarize important properties of model parameters and training data so that they can be used later without storing and/or iterating over the entire dataset. We consider estimating the Function Space Distance (FSD) over a training set, i.e. the average discrepancy between the outputs of two neural networks. We propose a Linearized Activation TRick (LAFTR) and derive an efficient approximation to FSD for ReLU neural networks.
  arXiv  Detail & Related papers  (2023-02-07T15:09:23Z)
• Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation [151.70234052015948]
  We propose a novel approach that encourages the optimization algorithm to seek a flat trajectory. We show that the weights trained on synthetic data are robust against the accumulated errors perturbations with the regularization towards the flat trajectory. Our method, called Flat Trajectory Distillation (FTD), is shown to boost the performance of gradient-matching methods by up to 4.7%.
  arXiv  Detail & Related papers  (2022-11-20T15:49:11Z)
• Efficient Dataset Distillation Using Random Feature Approximation [109.07737733329019]
  We propose a novel algorithm that uses a random feature approximation (RFA) of the Neural Network Gaussian Process (NNGP) kernel. Our algorithm provides at least a 100-fold speedup over KIP and can run on a single GPU. Our new method, termed an RFA Distillation (RFAD), performs competitively with KIP and other dataset condensation algorithms in accuracy over a range of large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-21T15:56:13Z)
• A Stochastic Bundle Method for Interpolating Networks [18.313879914379008]
  We propose a novel method for training deep neural networks that are capable of driving the empirical loss to zero. At each iteration our method constructs a maximum linear approximation, known as the bundle of the objective learning approximation.
  arXiv  Detail & Related papers  (2022-01-29T23:02:30Z)

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.