A Two-Step Disentanglement Method
This addresses the need for interpretable feature separation in machine learning, but it appears incremental as it builds on prior disentanglement solutions with a simpler approach.
The paper tackles the problem of disentangling data into label-correlated and label-uncorrelated factors, proposing a simpler two-step method using adversarial training that achieves utility on visual and financial datasets.
We address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not. Our solution is simpler than previous solutions and employs adversarial training. First, the part of the data that is correlated with the labels is extracted by training a classifier. Then, the other part is extracted such that it enables the reconstruction of the original data but does not contain label information. The utility of the new method is demonstrated on visual datasets as well as on financial data. Our code is available at https://github.com/naamahadad/A-Two-Step-Disentanglement-Method