Checklist 1. For all authors (a)

Do the main claims made in the abstract and introduction accurately reflect the paper's If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Y es] (b) Did you specify all the training details (e.g., data splits, hyperparameters, how they Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? Did you include the total amount of compute and the type of resources used (e.g., type Did you include any new assets either in the supplemental material or as a URL? [N/A] Did you discuss whether and how consent was obtained from people whose data you're If you used crowdsourcing or conducted research with human subjects... (a) We assume data are generated by Equation 12 which is the process adopted by Arjovsky et al. B.1 Implementation Resources Our implementations of EDNIL are in the repository All experiments were run on a GeForce RTX 3090 machine. The training time and GPU memory consumption of EDNIL are specified in Table 7. In Adult-Confounded and CMNIST, full-batch training is implemented due to enough memory space.