Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data

• URL: http://arxiv.org/abs/2108.05698v1
• Date: Wed, 11 Aug 2021 08:11:08 GMT
• Title: Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data
• Authors: Kuluhan Binici, Nam Trung Pham, Tulika Mitra, Karianto Leman
• Abstract summary: We propose a data-free KD framework that maintains a dynamic collection of generated samples over time. Our experiments demonstrate that we can improve the accuracy of the student models obtained via KD when compared with state-of-the-art approaches.
• Score: 5.064036314529226
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the increasing popularity of deep learning on edge devices, compressing large neural networks to meet the hardware requirements of resource-constrained devices became a significant research direction. Numerous compression methodologies are currently being used to reduce the memory sizes and energy consumption of neural networks. Knowledge distillation (KD) is among such methodologies and it functions by using data samples to transfer the knowledge captured by a large model (teacher) to a smaller one(student). However, due to various reasons, the original training data might not be accessible at the compression stage. Therefore, data-free model compression is an ongoing research problem that has been addressed by various works. In this paper, we point out that catastrophic forgetting is a problem that can potentially be observed in existing data-free distillation methods. Moreover, the sample generation strategies in some of these methods could result in a mismatch between the synthetic and real data distributions. To prevent such problems, we propose a data-free KD framework that maintains a dynamic collection of generated samples over time. Additionally, we add the constraint of matching the real data distribution in sample generation strategies that target maximum information gain. Our experiments demonstrate that we can improve the accuracy of the student models obtained via KD when compared with state-of-the-art approaches on the SVHN, Fashion MNIST and CIFAR100 datasets.

Related papers

• Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation [20.556083321381514]
  Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression. This paper introduces an innovative approach to DFKD through diverse diffusion augmentation (DDA) Comprehensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets showcase the superior performance of our method.
  arXiv  Detail & Related papers  (2024-10-23T07:01:16Z)
• Condensed Sample-Guided Model Inversion for Knowledge Distillation [42.91823325342862]
  Knowledge distillation (KD) is a key element in neural network compression that allows knowledge transfer from a pre-trained teacher model to a more compact student model. KD relies on access to the training dataset, which may not always be fully available due to privacy concerns or logistical issues related to the size of the data. In this paper, we consider condensed samples as a form of supplementary information, and introduce a method for using them to better approximate the target data distribution.
  arXiv  Detail & Related papers  (2024-08-25T14:43:27Z)
• Small Scale Data-Free Knowledge Distillation [37.708282211941416]
  We propose Small Scale Data-free Knowledge Distillation SSD-KD. SSD-KD balances synthetic samples and a priority sampling function to select proper samples. It can perform distillation training conditioned on an extremely small scale of synthetic samples.
  arXiv  Detail & Related papers  (2024-06-12T05:09:41Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• 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)
• 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)
• Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay [5.3330804968579795]
  Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Existing works use a validation set to monitor the accuracy of the student over real data and report the highest performance throughout the entire process. However, validation data may not be available at distillation time either, making it infeasible to record the student snapshot that achieved the peak accuracy. This is challenging because the student experiences knowledge degradation due to the distribution shift of the synthetic data. We propose to model the distribution of the previously observed synthetic samples
  arXiv  Detail & Related papers  (2022-01-09T14:14:28Z)
• Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation [51.66271681532262]
  Online Self-Acquired Knowledge Distillation (OSAKD) is proposed, aiming to improve the performance of any deep neural model in an online manner. We utilize k-nn non-parametric density estimation technique for estimating the unknown probability distributions of the data samples in the output feature space.
  arXiv  Detail & Related papers  (2021-08-26T14:01:04Z)
• Contrastive Model Inversion for Data-Free Knowledge Distillation [60.08025054715192]
  We propose Contrastive Model Inversion, where the data diversity is explicitly modeled as an optimizable objective. Our main observation is that, under the constraint of the same amount of data, higher data diversity usually indicates stronger instance discrimination. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that CMI achieves significantly superior performance when the generated data are used for knowledge distillation.
  arXiv  Detail & Related papers  (2021-05-18T15:13:00Z)
• MixKD: Towards Efficient Distillation of Large-scale Language Models [129.73786264834894]
  We propose MixKD, a data-agnostic distillation framework, to endow the resulting model with stronger generalization ability. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the error and the empirical error. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.
  arXiv  Detail & Related papers  (2020-11-01T18:47:51Z)
• Data-Free Network Quantization With Adversarial Knowledge Distillation [39.92282726292386]
  In this paper, we consider data-free network quantization with synthetic data. The synthetic data are generated from a generator, while no data are used in training the generator and in quantization. We show the gain of producing diverse adversarial samples by using multiple generators and multiple students.
  arXiv  Detail & Related papers  (2020-05-08T16:24:55Z)

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.