paper-with-me

홈 › Papers

Synthetic data generation method for data-free knowledge distillation in regression neural networks

2023-01-11 · Tianxun Zhou, Keng-Hwee Chiam

Knowledge distillation is the technique of compressing a larger neural network, known as the teacher, into a smaller neural network, known as the student, while still trying to maintain the performance of the larger neural network as much as possible. Existing methods of knowledge distillation are mostly applicable for classification tasks. Many of them also require access to the data used to train the teacher model. To address the problem of knowledge distillation for regression tasks under the absence of original training data, previous work has proposed a data-free knowledge distillation method where synthetic data are generated using a generator model trained adversarially against the student model. These synthetic data and their labels predicted by the teacher model are then used to train the student model. In this study, we investigate the behavior of various synthetic data generation methods and propose a new synthetic data generation strategy that directly optimizes for a large but bounded difference between the student and teacher model. Our results on benchmark and case study experiments demonstrate that the proposed strategy allows the student model to learn better and emulate the performance of the teacher model more closely.

📄 PDF Abstract BibTeX arXiv:2301.04338

Code (1)

zhoutianxun/data_free_kd_regression 공식 구현 pytorch

Tasks

Data-free Knowledge DistillationKnowledge DistillationregressionSynthetic Data Generation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

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

2021-08-11 · Kuluhan Binici, Nam Trung Pham, Tulika Mitra, Karianto Leman

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 compr…

Knowledge DistillationModel Compression

Knowledge-Guided Retrieval-Augmented Generation for Zero-Shot Psychiatric Data: Privacy Preserving Synthetic Data Generation

2026-03-26 · Adam Jakobsen, Sushant Gautam, Hugo Lewi Hammer, Susanne Olofsdotter 외 arxiv

AI systems in healthcare research have shown potential to increase patient throughput and assist clinicians, yet progress is constrained by limited access to real patient data. To address this issue, we present a zero-sh…

Synthetic Data GenerationTabular Data GenerationClinical Knowledge

Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation

2024-11-26 · Minh-Tuan Tran, Trung Le, Xuan-May Le, Jianfei Cai 외

Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. While DFKD methods have achieved success…

Data-free Knowledge DistillationDiversityKnowledge DistillationTransfer Learning

TAGAL: Tabular Data Generation using Agentic LLM Methods

2025-09-04 · Benoît Ronval, Pierre Dupont, Siegfried Nijssen arxiv

The generation of data is a common approach to improve the performance of machine learning tasks, among which is the training of models for classification. In this paper, we present TAGAL, a collection of methods able to…

Tabular Data Generation

Hybrid Data-Free Knowledge Distillation

2024-12-18 · Jialiang Tang, Shuo Chen, Chen Gong

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-…

Data-free Knowledge DistillationGenerative Adversarial NetworkKnowledge DistillationRepresentation Learning