paper-with-me

홈 › Papers

SEMRes-DDPM: Residual Network Based Diffusion Modelling Applied to Imbalanced Data

2024-03-09 · Ming Zheng, Yang Yang, Zhi-Hang Zhao, Shan-Chao Gan, Yang Chen, Si-Kai Ni, Yang Lu

In the field of data mining and machine learning, commonly used classification models cannot effectively learn in unbalanced data. In order to balance the data distribution before model training, oversampling methods are often used to generate data for a small number of classes to solve the problem of classifying unbalanced data. Most of the classical oversampling methods are based on the SMOTE technique, which only focuses on the local information of the data, and therefore the generated data may have the problem of not being realistic enough. In the current oversampling methods based on generative networks, the methods based on GANs can capture the true distribution of data, but there is the problem of pattern collapse and training instability in training; in the oversampling methods based on denoising diffusion probability models, the neural network of the inverse diffusion process using the U-Net is not applicable to tabular data, and although the MLP can be used to replace the U-Net, the problem exists due to the simplicity of the structure and the poor effect of removing noise. problem of poor noise removal. In order to overcome the above problems, we propose a novel oversampling method SEMRes-DDPM.In the SEMRes-DDPM backward diffusion process, a new neural network structure SEMST-ResNet is used, which is suitable for tabular data and has good noise removal effect, and it can generate tabular data with higher quality. Experiments show that the SEMResNet network removes noise better than MLP; SEMRes-DDPM generates data distributions that are closer to the real data distributions than TabDDPM with CWGAN-GP; on 20 real unbalanced tabular datasets with 9 classification models, SEMRes-DDPM improves the quality of the generated tabular data in terms of three evaluation metrics (F1, G-mean, AUC) with better classification performance than other SOTA oversampling methods.

📄 PDF Abstract BibTeX arXiv:2403.05918

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
SMOTE Perhaps the most widely used approach to synthesizing new examples is called the Synthetic Minority Oversampling Technique, or SMOTE for short. This technique was described by…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

TabDDPM: Modelling Tabular Data with Diffusion Models

2022-09-30 · Akim Kotelnikov, Dmitry Baranchuk, Ivan Rubachev, Artem Babenko

Denoising diffusion probabilistic models are currently becoming the leading paradigm of generative modeling for many important data modalities. Being the most prevalent in the computer vision community, diffusion models …

Denoising

Bring the Power of Diffusion Model to Defect Detection

2024-08-25 · Xuyi Yu

Due to the high complexity and technical requirements of industrial production processes, surface defects will inevitably appear, which seriously affects the quality of products. Although existing lightweight detection n…

Defect DetectionDenoisingKnowledge Distillation

ResEnsemble-DDPM: Residual Denoising Diffusion Probabilistic Models for Ensemble Learning

2023-12-04 · Shi Zhenning, Dong Changsheng, Xie Xueshuo, Pan Bin 외

Nowadays, denoising diffusion probabilistic models have been adapted for many image segmentation tasks. However, existing end-to-end models have already demonstrated remarkable capabilities. Rather than using denoising d…

DenoisingEnsemble LearningImage GenerationImage Segmentation+2

Diffusion Priors In Variational Autoencoders

2021-06-29 · ICML Workshop INNF 2021 7 · Antoine Wehenkel, Gilles Louppe

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by compet…

Denoising

AniRes2D: Anisotropic Residual-enhanced Diffusion for 2D MR Super-Resolution

2023-12-07 · Zejun Wu, Samuel W. Remedios, Blake E. Dewey, Aaron Carass 외

Anisotropic low-resolution (LR) magnetic resonance (MR) images are fast to obtain but hinder automated processing. We propose to use denoising diffusion probabilistic models (DDPMs) to super-resolve these 2D-acquired LR …

DenoisingSuper-Resolution