Do-Operation Guided Causal Representation Learning with Reduced Supervision Strength

arxiv(2022)

引用 0|浏览25
暂无评分
摘要
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.
更多
查看译文
关键词
representation,learning,do-operation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要