Do-Operation Guided Causal Representation Learning with Reduced Supervision Strength
This work addresses a bottleneck in causal representation learning for researchers by reducing the need for extensive labeled data, though it appears incremental as it builds on existing methods.
The paper tackles the problem of causal representation learning requiring large labeled datasets by using do-operations to reduce supervision strength, achieving superior performance compared to state-of-the-art methods on synthetic and real datasets.
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.