A Unified Framework for Generative Data Augmentation: A Comprehensive Survey

TL;DR

This document provides a practical guide to the elsarticle.cls LaTeX class used for Elsevier journal submissions, explaining its motivation to minimize package conflicts and its compatibility with standard LaTeX packages. It contrasts elsarticle.cls with the older elsart.cls, highlighting improvements in structure, citation handling, and formatting options across preprint and final styles. Installation workflow and distribution sources are described in detail, including generating the class from the provided dtx/ins files and integrating it into the TeX tree. The discussion emphasizes flexibility for formatting, floating environments, and compatibility with amsmath and hyperref features, facilitating reliable manuscript preparation for Elsevier journals.

Abstract

Generative data augmentation (GDA) has emerged as a promising technique to alleviate data scarcity in machine learning applications. This thesis presents a comprehensive survey and unified framework of the GDA landscape. We first provide an overview of GDA, discussing its motivation, taxonomy, and key distinctions from synthetic data generation. We then systematically analyze the critical aspects of GDA - selection of generative models, techniques to utilize them, data selection methodologies, validation approaches, and diverse applications. Our proposed unified framework categorizes the extensive GDA literature, revealing gaps such as the lack of universal benchmarks. The thesis summarises promising research directions, including , effective data selection, theoretical development for large-scale models' application in GDA and establishing a benchmark for GDA. By laying a structured foundation, this thesis aims to nurture more cohesive development and accelerate progress in the vital arena of generative data augmentation.