Learning Independent Causal Mechanisms
Learning Independent Causal Mechanisms
复制标题
DOI：
--
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
Giambattista Parascandolo;Mateo Rojas-Carulla;Niki Kilbertus;B. Scholkopf
中科院分区：
文献类型：
--
作者：
Giambattista Parascandolo;Mateo Rojas-Carulla;Niki Kilbertus;B. Scholkopf
统计学习依赖于从分布中采样的数据，我们通常不关心最初实际生成它的是什么。从因果模型的角度来看，每个分布的结构都是由引起可观察量之间依赖性的物理机制引起的。然而，机制可以是生成模型的有意义的自主模块，其意义超出了特定的必然数据分布，有助于在问题之间进行转移。我们开发了一种算法，可以从一组转换后的数据点中恢复一组独立（逆）机制。该方法是无人监督的，并且基于一组专家，这些专家竞争机制生成的数据，从而推动专业化。我们在一系列图像数据实验中分析了所提出的方法。每个专家都会学习将转换后的数据的子集映射回参考分布。学到的机制可以推广到新的领域。我们讨论迁移学习的影响以及与生成建模最新趋势的联系。
Statistical learning relies upon data sampled from a distribution, and we usually do not care what actually generated it in the first place. From the point of view of causal modeling, the structure of each distribution is induced by physical mechanisms that give rise to dependences between observables. Mechanisms, however, can be meaningful autonomous modules of generative models that make sense beyond a particular entailed data distribution, lending themselves to transfer between problems. We develop an algorithm to recover a set of independent (inverse) mechanisms from a set of transformed data points. The approach is unsupervised and based on a set of experts that compete for data generated by the mechanisms, driving specialization. We analyze the proposed method in a series of experiments on image data. Each expert learns to map a subset of the transformed data back to a reference distribution. The learned mechanisms generalize to novel domains. We discuss implications for transfer learning and links to recent trends in generative modeling.