Weakly Supervised Disentanglement by Pairwise Similarities
This work addresses the challenge of reliably recovering factors of interest in generative models for researchers and practitioners, representing an incremental advancement in supervised disentanglement methods.
The paper tackles the problem of unsupervised disentanglement learning lacking guarantees by introducing weak supervision through pairwise similarities, and demonstrates that this approach substantially improves disentanglement performance.
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered. Motivated by a real-world problem, we propose a setting where the user introduces weak supervision by providing similarities between instances based on a factor to be disentangled. The similarity is provided as either a binary (yes/no) or a real-valued label describing whether a pair of instances are similar or not. We propose a new method for weakly supervised disentanglement of latent variables within the framework of Variational Autoencoder. Experimental results demonstrate that utilizing weak supervision improves the performance of the disentanglement method substantially.