Bias and Generalization in Deep Generative Models: An Empirical Study
Bias and Generalization in Deep Generative Models: An Empirical Study
复制标题
DOI：
--
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Shengjia Zhao;Hongyu Ren;Arianna Yuan;Jiaming Song;Noah D. Goodman;Stefano Ermon
中科院分区：
文献类型：
--
作者：
Shengjia Zhao;Hongyu Ren;Arianna Yuan;Jiaming Song;Noah D. Goodman;Stefano Ermon
在高维环境中，密度估计算法主要依赖于它们的归纳偏置。尽管最近在经验上取得了成功，但深度生成模型的归纳偏差还没有得到很好的理解。在本文中，我们提出了一个框架来系统地研究图像深度生成模型中的偏见和泛化。受认知心理学实验方法的启发，我们用精心设计的训练数据集探索每种学习算法，以表征现有模型何时以及如何生成新属性及其组合。我们确定了与人类心理的相似之处，并验证这些模式在常用的模型和体系结构中是一致的。
In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models of images. Inspired by experimental methods from cognitive psychology, we probe each learning algorithm with carefully designed training datasets to characterize when and how existing models generate novel attributes and their combinations. We identify similarities to human psychology and verify that these patterns are consistent across commonly used models and architectures.