Learning Adversarially Fair and Transferable Representations
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We 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 and demonstrate empirically that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.
Code (7)
Tasks
FairnessRepresentation LearningTransfer LearningSimilar Papers 제목 키워드 기반
Learning Controllable Fair Representations
Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility of the data. We propose an information-th…
FairnessClosing the Gender Wage Gap: Adversarial Fairness in Job Recommendation
The goal of this work is to help mitigate the already existing gender wage gap by supplying unbiased job recommendations based on resumes from job seekers. We employ a generative adversarial network to remove gender bias…
FairnessGenerative Adversarial NetworkRecommendation Systems10 Years of Fair Representations: Challenges and Opportunities
Fair Representation Learning (FRL) is a broad set of techniques, mostly based on neural networks, that seeks to learn new representations of data in which sensitive or undesired information has been removed. Methodologic…
Aspect Sentiment Triplet ExtractionAutoMLLearning TheoryRepresentation LearningFrom Discrete to Continuous: Deep Fair Clustering With Transferable Representations
We consider the problem of deep fair clustering, which partitions data into clusters via the representations extracted by deep neural networks while hiding sensitive data attributes. To achieve fairness, existing methods…
ClusteringFairnessFairness-aware Regression Robust to Adversarial Attacks
In this paper, we take a first step towards answering the question of how to design fair machine learning algorithms that are robust to adversarial attacks. Using a minimax framework, we aim to design an adversarially ro…
Fairnessregression