Post-Pruning Accuracy Recovery via Data-Free Knowledge Distillation

• URL: http://arxiv.org/abs/2511.20702v1
• Date: Mon, 24 Nov 2025 18:27:40 GMT
• Title: Post-Pruning Accuracy Recovery via Data-Free Knowledge Distillation
• Authors: Chinmay Tripurwar, Utkarsh Maurya, Dishant,
• Abstract summary: In privacy-sensitive domains such as healthcare or finance, access to the original training data is often restricted post-deployment due to regulations.<n>This paper proposes a Data-Free Knowledge Distillation framework to bridge the gap between model compression and data privacy.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model pruning is a widely adopted technique to reduce the computational complexity and memory footprint of Deep Neural Networks (DNNs). However, global unstructured pruning often leads to significant degradation in accuracy, typically necessitating fine-tuning on the original training dataset to recover performance. In privacy-sensitive domains such as healthcare or finance, access to the original training data is often restricted post-deployment due to regulations (e.g., GDPR, HIPAA). This paper proposes a Data-Free Knowledge Distillation framework to bridge the gap between model compression and data privacy. We utilize DeepInversion to synthesize privacy-preserving ``dream'' images from the pre-trained teacher model by inverting Batch Normalization (BN) statistics. These synthetic images serve as a transfer set to distill knowledge from the original teacher to the pruned student network. Experimental results on CIFAR-10 across various architectures (ResNet, MobileNet, VGG) demonstrate that our method significantly recovers accuracy lost during pruning without accessing a single real data point.

Related papers

• TIP: Resisting Gradient Inversion via Targeted Interpretable Perturbation in Federated Learning [8.156452885913108]
  Federated Learning (FL) facilitates collaborative model training while preserving data locality.<n>The exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs)<n>We propose Targeted Interpretable Perturbation (TIP), a novel defense framework that integrates model interpretability with frequency domain analysis.
  arXiv  Detail & Related papers  (2026-02-12T06:32:49Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models [45.10098466182961]
  ReCIT is a novel privacy attack that achieves recovery of emphfull private data from PEFT gradients with high fidelity.<n>It consistently outperforms state-of-the-art memorization and inversion-based attacks across different PEFT paradigms.
  arXiv  Detail & Related papers  (2025-04-29T09:23:19Z)
• Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction [48.30341580103962]
  We propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues.<n>We design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction.<n> Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-07T12:29:32Z)
• One-shot Federated Learning via Synthetic Distiller-Distillate Communication [63.89557765137003]
  One-shot Federated learning (FL) is a powerful technology facilitating collaborative training of machine learning models in a single round of communication.<n>We propose FedSD2C, a novel and practical one-shot FL framework designed to address these challenges.
  arXiv  Detail & Related papers  (2024-12-06T17:05:34Z)
• GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search [52.27057178618773]
  Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients.<n>A majority of gradient inversion methods rely heavily on explicit prior knowledge, which is often unavailable in realistic scenarios.<n>We propose Neural Architecture Search (GI-NAS), which adaptively searches the network and captures the implicit priors behind neural architectures.
  arXiv  Detail & Related papers  (2024-05-31T09:29:43Z)
• Distilling the Knowledge in Data Pruning [4.720247265804016]
  We explore the application of data pruning while incorporating knowledge distillation (KD) when training on a pruned subset. We demonstrate significant improvement across datasets, pruning methods, and on all pruning fractions. We make an intriguing observation: when using lower pruning fractions, larger teachers lead to accuracy degradation, while surprisingly, employing teachers with a smaller capacity than the student's may improve results.
  arXiv  Detail & Related papers  (2024-03-12T17:44:45Z)
• Dataset Quantization [72.61936019738076]
  We present dataset quantization (DQ), a new framework to compress large-scale datasets into small subsets. DQ is the first method that can successfully distill large-scale datasets such as ImageNet-1k with a state-of-the-art compression ratio.
  arXiv  Detail & Related papers  (2023-08-21T07:24:29Z)
• Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning [12.982673904306633]
  We propose a novel framework named Unified Data-Free Compression(UDFC), which performs pruning and quantization simultaneously without any data and fine-tuning process. We evaluate the UDFC on the large-scale image classification task and obtain significant improvements over various network architectures and compression methods.
  arXiv  Detail & Related papers  (2023-08-14T15:25:07Z)
• Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay [52.251188477192336]
  Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep learning system to incrementally learn new classes with limited data. We show through empirical results that adopting the data replay is surprisingly favorable. We propose using data-free replay that can synthesize data by a generator without accessing real data.
  arXiv  Detail & Related papers  (2022-07-22T17:30:51Z)
• 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)

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.