Outlier Generation

2000년 도입 · 논문 1편에서 사용

A group of methods designed to generate outliers in tabular data, emphasizing the importance of such techniques as supported by extreme value theory. These methods are crucial for modeling, analyzing, and understanding anomalous or rare events within structured datasets.

출처: zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation

소개 논문: zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation