论文阅读 [TPAMI-2022] Generative Imputation and Stochastic Prediction

论文阅读 [TPAMI-2022] Generative Imputation and Stochastic Prediction

论文搜索(studyai.com)

搜索论文: Generative Imputation and Stochastic Prediction

搜索论文: http://www.studyai.com/search/whole-site/?q=Generative+Imputation+and+Stochastic+Prediction

关键字(Keywords)

Uncertainty; Generators; Stochastic processes; Training; Data models; Task analysis; Generative adversarial networks; Missing data; imputation; incomplete data; generative adversarial networks; classification uncertainty

机器学习; 机器视觉; 自然语言处理

生成对抗; 同义词; 缺失值补全

摘要(Abstract)

In many machine learning applications, we are faced with incomplete datasets.

在许多机器学习应用中，我们面临着不完整的数据集。.

In the literature, missing data imputation techniques have been mostly concerned with filling missing values.

在文献中，缺失数据插补技术主要涉及填补缺失值。.

However, the existence of missing values is synonymous with uncertainties not only over the distribution of missing values but also over target class assignments that require careful consideration.

然而，缺失值的存在不仅意味着缺失值分布的不确定性，还意味着需要仔细考虑的目标类作业的不确定性。.

In this paper, we propose a simple and effective method for imputing missing features and estimating the distribution of target assignments given incomplete data.

在本文中，我们提出了一种简单有效的方法，用于在不完全数据的情况下填充缺失特征和估计目标分配的分布。.

In order to make imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish.

为了进行插补，我们训练了一个简单有效的生成网络来生成插补，而鉴别器网络的任务是识别插补。.

Following this, a predictor network is trained using the imputed samples from the generator network to capture the classification uncertainties and make predictions accordingly.

然后，使用生成器网络中的输入样本对预测网络进行训练，以捕获分类不确定性并做出相应的预测。.

The proposed method is evaluated on CIFAR-10 and MNIST image datasets as well as five real-world tabular classification datasets, under different missingness rates and structures.

在不同的丢失率和结构下，在CIFAR-10和MNIST图像数据集以及五个真实的表格分类数据集上对所提出的方法进行了评估。.

Our experimental results show the effectiveness of the proposed method in generating imputations as well as providing estimates for the class uncertainties in a classification task when faced with missing values…

我们的实验结果表明，当面临缺失值时，该方法在生成插补以及为分类任务中的类别不确定性提供估计方面是有效的。。.

作者(Authors)

[‘Mohammad Kachuee’, ‘Kimmo Karkkainen’, ‘Orpaz Goldstein’, ‘Sajad Darabi’, ‘Majid Sarrafzadeh’]