Learning Interpretable Representations with Informative Entanglements-猫眼课题宝

DOI：

10.24963/ijcai.2020/273

发表时间：

2020-07

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Yifan Hao;H. Cao

在无监督环境下学习可解释表征是一项重要而又具有挑战性的任务。现有的无监督可解释方法侧重于从数据中提取独立的显著特征。然而，他们忽略了一个事实，即显著特征的纠缠也可能提供信息。承认这些纠缠可以提高可解释性，从而提取更高质量和更广泛的显著特征。在本文中，我们提出了一种新的方法，使生成性对抗网络(GANS)能够以信息的方式发现可能纠缠的显著特征，而不是只提取解缠的特征。具体地说，我们提出了一种正则化方法来惩罚训练时提取的特征交互与给定的依赖结构之间的不一致。我们使用贝叶斯网络对这些交互进行建模，估计最大似然参数，并计算负似然分数来衡量分歧。在使用合成数据集和真实世界数据集对所提出的方法进行定性和定量评估后，我们证明了我们提出的正则化方法引导Gans学习具有与最新技术竞争的解缠分数的表示，同时提取更广泛的显著特征。

Learning interpretable representations in an unsupervised setting is an important yet a challenging task. Existing unsupervised interpretable methods focus on extracting independent salient features from data. However they miss out the fact that the entanglement of salient features may also be informative. Acknowledging these entanglements can improve the interpretability, resulting in extraction of higher quality and a wider variety of salient features. In this paper, we propose a new method to enable Generative Adversarial Networks (GANs) to discover salient features that may be entangled in an informative manner, instead of extracting only disentangled features. Specifically, we propose a regularizer to punish the disagreement between the extracted feature interactions and a given dependency structure while training. We model these interactions using a Bayesian network, estimate the maximum likelihood parameters and calculate a negative likelihood score to measure the disagreement. Upon qualitatively and quantitatively evaluating the proposed method using both synthetic and real-world datasets, we show that our proposed regularizer guides GANs to learn representations with disentanglement scores competing with the state-of-the-art, while extracting a wider variety of salient features.

Learning Interpretable Representations with Informative Entanglements

文献摘要

相似文献