Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
How can we learn a classifier that is "fair" for a protected or sensitive group, when we do not know if the input to the classifier belongs to the protected group? How can we train such a classifier when data on the protected group is difficult to attain? In many settings, finding out the sensitive input attribute can be prohibitively expensive even during model training, and sometimes impossible during model serving. For example, in recommender systems, if we want to predict if a user will click on a given recommendation, we often do not know many attributes of the user, e.g., race or age, and many attributes of the content are hard to determine, e.g., the language or topic. Thus, it is not feasible to use a different classifier calibrated based on knowledge of the sensitive attribute. Here, we use an adversarial training procedure to remove information about the sensitive attribute from the latent representation learned by a neural network. In particular, we study how the choice of data for the adversarial training effects the resulting fairness properties. We find two interesting results: a small amount of data is needed to train these adversarial models, and the data distribution empirically drives the adversary's notion of fairness.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeFairnessRecommendation SystemsSimilar Papers 제목 키워드 기반
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient health and road safety, it is imperative to maintain both high adversarial robustness…
Adversarial DefenseAdversarial RobustnessAutonomous DrivingConformal Prediction+3Provable tradeoffs in adversarially robust classification
It is well known that machine learning methods can be vulnerable to adversarially-chosen perturbations of their inputs. Despite significant progress in the area, foundational open problems remain. In this paper, we addre…
ClassificationGeneral ClassificationRobust classificationUsing Machine Bias To Measure Human Bias
Biased human decisions have consequential impacts across various domains, yielding unfair treatment of individuals and resulting in suboptimal outcomes for organizations and society. In recognition of this fact, organiza…
Decision MakingRobust Fast Adaptation from Adversarially Explicit Task Distribution Generation
Meta-learning is a practical learning paradigm to transfer skills across tasks from a few examples. Nevertheless, the existence of task distribution shifts tends to weaken meta-learners' generalization capability, partic…
Meta-LearningOn the Trade-offs between Adversarial Robustness and Actionable Explanations
As machine learning models are increasingly being employed in various high-stakes settings, it becomes important to ensure that predictions of these models are not only adversarially robust, but also readily explainable …
Adversarial Robustness