On Disentangled Representations Learned From Correlated Data
The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream applications of disentanglement such as fairness. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.
Code (2)
Tasks
DisentanglementFairnessSimilar Papers 제목 키워드 기반
On Disentangled and Locally Fair Representations
We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. This problem is tackled through the lens of disentangled and locally fair representations. We lear…
AttributeFairnessBe More Active! Understanding the Differences between Mean and Sampled Representations of Variational Autoencoders
The ability of Variational Autoencoders to learn disentangled representations has made them appealing for practical applications. However, their mean representations, which are generally used for downstream tasks, have r…
DisentanglementOn the Fairness of Disentangled Representations
Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks. In this pap…
DisentanglementFairnessConditional Mutual Information for Disentangled Representations in Reinforcement Learning
Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these…
continuous-controlContinuous ControlDisentanglementreinforcement-learning+2Scaling-up Disentanglement for Image Translation
Image translation methods typically aim to manipulate a set of labeled attributes (given as supervision at training time e.g. domain label) while leaving the unlabeled attributes intact. Current methods achieve either: (…
DisentanglementDiversityTranslation