.png){kind=icon}
返回
Controllable Data Generation by Deep Learning: A Review
.png){kind=icon}
OA
AI
DOI：10.1145/3648609.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Designing and generating new data under targeted properties has been attracting various critical applications such as molecule design, image editing and speech synthesis. Traditional hand-crafted approaches heavily rely on expertise experience and intensive human efforts, yet still suffer from the insufficiency of scientific knowledge and low throughput to support effective and efficient data generation. Recently, the advancement of deep learning has created the opportunity for expressive methods to learn the underlying representation and properties of data. Such capability provides new ways of determining the mutual relationship between the structural patterns and functional properties of the data and leveraging such relationships to generate structural data, given the desired properties. This article is a systematic review that explains this promising research area, commonly known as controllable deep data generation. First, the article raises the potential challenges and provides preliminaries. Then the article formally defines controllable deep data generation, proposes a taxonomy on various techniques and summarizes the evaluation metrics in this specific domain. After that, the article introduces exciting applications of controllable deep data generation, experimentally analyzes and compares existing works. Finally, this article highlights the promising future directions of controllable deep data generation and identifies five potential challenges.
Keyword:
Data generation
deep learning
deep generative models
property controllable generation
期刊
IF:
28
论文数:
2.5K
被引数:
3.5W
机构
引用论文
.png){kind=icon}
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns深度化学的深度学习: 优化化学模式的预测
OAAI
OAAI分享收藏
查看更多内容