论文标题
进行操作指导因果代表学习，并降低监督力量
Do-Operation Guided Causal Representation Learning with Reduced Supervision Strength
论文作者
论文摘要
已提出了因果表示学习，以编码高维数据中提出的因素之间的关系。但是，现有方法仅使用大量标记的数据而遭受的影响，而忽略了相同因果机制产生的样本遵循相同的因果关系的事实。在本文中，我们试图通过利用操作来降低监督力量来探索此类信息。我们提出了一个框架，该框架通过交换从一对输入中编码的潜在因果因素来实现操作。此外，我们还从经验和理论上确定了现有因果表示指标的不足，并引入了新的指标以更好地评估。在合成数据集和真实数据集上进行的实验证明了我们方法的优势与最先进的方法相比。
Causal representation learning has been proposed to encode relationships between factors presented in the high dimensional data. However, existing methods suffer from merely using a large amount of labeled data and ignore the fact that samples generated by the same causal mechanism follow the same causal relationships. In this paper, we seek to explore such information by leveraging do-operation to reduce supervision strength. We propose a framework that implements do-operation by swapping latent cause and effect factors encoded from a pair of inputs. Moreover, we also identify the inadequacy of existing causal representation metrics empirically and theoretically and introduce new metrics for better evaluation. Experiments conducted on both synthetic and real datasets demonstrate the superiorities of our method compared with state-of-the-art methods.
