Federated Traffic Synthesizing and Classification Using Generative Adversarial Networks

Xu, Chenxin; Xia, Rong; Xiao, Yong; Li, Yingyu; Shi, Guangming; Chen, Kwang-Cheng

doi:10.1109/icc42927.2021.9500866

Cited by 16 publications

(28 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adopt two different versions of the GANs (tabular [40] and conditional [41]) for mixed data synthesis. Each GAN is briefly described below.…”

Section: A Gans For Tabular Datamentioning

confidence: 99%

“…Generating tabular data is a challenge compared to images as they contain various types of data, such as categorical, numerical, text, time, and cross table references [40]. To generate synthetic data using TGAN, consider a table 𝑇 with mixed data (numerical {𝑛1, 𝑛2, … } and categorical {𝑐1, 𝑐2, .…”

Section: ) Tabular Ganmentioning

confidence: 99%

“…. }) that have a joint probability distribution of 𝑃(𝑛1, 𝑛2 … 𝐶1, 𝑐2, … ) with each row being one sample distribution from the joint distribution [40]. Both the numerical and categorical data are preprocessed such that the numerical values in the dataset are normalized to [-1, 1].…”

Section: ) Tabular Ganmentioning

confidence: 99%

“…Both the numerical and categorical data are preprocessed such that the numerical values in the dataset are normalized to [-1, 1]. Furthermore, to handle multimodal distributions, modespecific normalization with five modes is used based on the Gaussian mixture model (GMM) [40]. For categorical data generation, a sample from |𝐶 𝑖 | as the categorical variable is first converted into a one-hot vector 𝑐 𝑖,𝑗 , and uniform noise is added to each dimension followed by renormalizing the representation as 𝑐 𝑖,𝑗 ⃪ 𝑐 𝑖,𝑗 ∑ 𝑑 𝑖,𝑗…”

Section: ) Tabular Ganmentioning

confidence: 99%

“…Multiple modified versions of the GAN are introduced to synthesize new data for both images and tabular data. This paper uses two versions of GANs (TGAN [40] and CTGAN [41]) to oversample tabular data. The major contributions of this paper are summarized as follows:…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Mixed Data Imputation Using Generative Adversarial Networks

et al. 2022

View full text Add to dashboard Cite

Missing values are common in real-world datasets and pose a significant challenge to the performance of statistical and machine learning models. Generally, missing values are imputed using statistical methods, such as the mean, median, mode, or machine learning approaches. These approaches are limited to either numerical or categorical data. Imputation in mixed datasets that contain both numerical and categorical attributes is challenging and has received little attention. Machine learning-based imputation algorithms usually require a large amount of training data. However, obtaining such data is difficult. Furthermore, no considerate work has been conducted in the literature that focuses on the effects of the training and testing size with an increasing amount of missing data. To address this gap, we propose that increasing the amount of training data will improve the imputation performance. We first used generative adversarial network (GAN) methods to increase the amount of training data. We considered two state-of-theart GANs (tabular and conditional tabular) to add synthetic samples using observed data with different synthetic sample ratios. We then used three state-of-the-art imputation models that can handle mixed data: MissForest, multivariate imputation by chained equations, and denoising auto encoder (DAE). We propose a robust experimental setup on four publicly available datasets with different training-testing data divisions that have increasing missingness ratios. Extensive experimental results show that incorporating synthetic samples with training data achieves better performance compared to the baseline methods for mixed data imputation in both categorical and numerical variables, especially for large missingness ratios.

show abstract

“…We adopt two different versions of the GANs (tabular [40] and conditional [41]) for mixed data synthesis. Each GAN is briefly described below.…”

Section: A Gans For Tabular Datamentioning

confidence: 99%

Section: ) Tabular Ganmentioning

confidence: 99%

Section: ) Tabular Ganmentioning

confidence: 99%

Section: ) Tabular Ganmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Mixed Data Imputation Using Generative Adversarial Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

Streaming traffic classification: a hybrid deep learning and big data approach

Seydali,

Khunjush,

Dogani

2024

Cluster Comput

View full text Add to dashboard Cite

Black-Box Model Risk in Finance

Cohen¹,

Snow²,

Szpruch³

2023

Machine Learning and Data Sciences for Financial Markets

View full text Add to dashboard Cite

Machine learning models are increasingly used in a wide variety of financial settings. The difficulty of understanding the inner workings of these systems, combined with their wide applicability, has the potential to lead to significant new risks for users; these risks need to be understood and quantified. In this chapter, we will focus on a well studied application of machine learning techniques, to pricing and hedging of financial options. Our aim will be to highlight the various sources of risk that the introduction of machine learning emphasises or de-emphasises, and the possible risk mitigation and management strategies that are available.

show abstract

Federated Traffic Synthesizing and Classification Using Generative Adversarial Networks

Cited by 16 publications

References 13 publications

Mixed Data Imputation Using Generative Adversarial Networks

Mixed Data Imputation Using Generative Adversarial Networks

Streaming traffic classification: a hybrid deep learning and big data approach

Black-Box Model Risk in Finance

Contact Info

Product

Resources

About