BriefGPT.xyz
Oct, 2019
带保证的弱监督解缠模型
Weakly Supervised Disentanglement with Guarantees
HTML
PDF
Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole
TL;DR
研究了当领域匹配、限定标签、匹配对和rank-pairing等弱监督方法与基于分布匹配的学习算法相结合时，弱监督何时以及如何保证解缠缚表示的理论框架及其保证和局限性，并通过实验证明了我们理论框架的预测能力和有用性。
Abstract
Learning
disentangled representations
that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning. Recently, concerns about the viability of learning
d
→