Despite impressive progress in the last decade, it still remains an open challenge to build models that generalize well across multiple tasks and datasets. One path to achieve this is to learn meaningful and compact representations, in which different semantic aspects of data are structurally disentangled. The focus of disentanglement approaches has been on separating independent factors of variation despite the fact that real-world observations are often not structured into meaningful independent causal variables to begin with. In this work we bridge the gap to real-world scenarios by analyzing the behavior of most prominent methods and disentanglement scores on correlated data in a large scale empirical study (including 3900 models). We show that systematically induced correlations in the dataset are being learned and reflected in the latent representations, while widely used disentanglement scores fall short of capturing these latent correlations. Finally, we demonstrate how to disentangle these latent correlations using weak supervision, even if we constrain this supervision to be causally plausible. Our results thus support the argument to learn independent mechanisms rather than independent factors of variations.

In this work, we present causal directed acyclic graphs (DAGs) as a unifying framework for the recent literature on fairness in dynamical systems. We advocate for the use of causal DAGs as a tool in both designing equitable policies and estimating their impacts. By visualizing models of dynamic unfairness graphically, we expose implicit causal assumptions which can then be more easily interpreted and scrutinized by domain experts. We demonstrate that this method of reinterpretation can be used to critique the robustness of an existing model/policy, or uncover new policy evaluation questions. Causal models also enable a rich set of options for evaluating a new candidate policy without incurring the risk of implementing the policy in the real world. We close the paper with causal analyses of several models from the recent literature, and provide an in-depth case study to demonstrate the utility of causal DAGs for modeling fairness in dynamical systems.

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also \emph{flexibly fair}, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder---which does not require the sensitive attributes for inference---enables the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.

How do we learn from biased data? Historical datasets often reflect historical prejudices; sensitive or protected attributes may affect the observed treatments and outcomes. Classification algorithms tasked with predicting outcomes accurately from these datasets tend to replicate these biases. We advocate a causal modeling approach to learning from biased data and reframe fair classification as an intervention problem. We propose a causal model in which the sensitive attribute confounds both the treatment and the outcome. Building on prior work in deep learning and generative modeling, we describe how to learn the parameters of this causal model from observational data alone, even in the presence of unobserved confounders. We show experimentally that fairness-aware causal modeling provides better estimates of the causal effects between the sensitive attribute, the treatment, and the outcome. We further present evidence that estimating these causal effects can help us to learn policies which are both more accurate and fair, when presented with a historically biased dataset.

In this work, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. We envision a scenario where learned representations may be handed off to other entities with unknown objectives. We propose and explore adversarial representation learning as a natural method of ensuring those entities will act fairly, and connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair prediction. Furthermore, we present the first in-depth experimental demonstration of fair transfer learning, by showing that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.