Learning Neurosymbolic Generative Models via Program Synthesis
Learning Neurosymbolic Generative Models via Program Synthesis
复制标题
DOI：
--
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
Halley Young;O. Bastani;M. Naik
中科院分区：
文献类型：
--
作者：
Halley Young;O. Bastani;M. Naik
近年来，在设计更好的生成模型方面已取得了长足的进步。但是，尽管取得了这种进步，但最先进的方法仍然无法捕获数据中的复杂全球结构。例如，建筑物的图像通常包含空间图案，例如定期重复窗口；最先进的生成方法无法轻易复制这些结构。我们建议通过将代表全局结构的程序合并到生成模型中来解决此问题 - 此外，我们提出了一个通过利用程序合成来生成培训数据来学习这些模型的框架。在综合和现实世界中，我们证明了我们的方法在生成和完成包含全局结构的图像中的最新图像要好得多。
Significant strides have been made toward designing better generative models in recent years. Despite this progress, however, state-of-the-art approaches are still largely unable to capture complex global structure in data. For example, images of buildings typically contain spatial patterns such as windows repeating at regular intervals; state-of-the-art generative methods can't easily reproduce these structures. We propose to address this problem by incorporating programs representing global structure into the generative model---e.g., a 2D for-loop may represent a configuration of windows. Furthermore, we propose a framework for learning these models by leveraging program synthesis to generate training data. On both synthetic and real-world data, we demonstrate that our approach is substantially better than the state-of-the-art at both generating and completing images that contain global structure.