Learning Interpretable Fair Representations
Numerous approaches have been recently proposed for learning fair representations that mitigate unfair outcomes in prediction tasks. A key motivation for these methods is that the representations can be used by third parties with unknown objectives. However, because current fair representations are generally not interpretable, the third party cannot use these fair representations for exploration, or to obtain any additional insights, besides the pre-contracted prediction tasks. Thus, to increase data utility beyond prediction tasks, we argue that the representations need to be fair, yet interpretable. We propose a general framework for learning interpretable fair representations by introducing an interpretable "prior knowledge" during the representation learning process. We implement this idea and conduct experiments with ColorMNIST and Dsprite datasets. The results indicate that in addition to being interpretable, our representations attain slightly higher accuracy and fairer outcomes in a downstream classification task compared to state-of-the-art fair representations.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionRepresentation LearningSimilar Papers 제목 키워드 기반
Learning Fair and Interpretable Representations via Linear Orthogonalization
To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms. However, recent research suggests that this does not remove discrimination, and can perpetuate harmful stereoty…
FairnessLearning Representational Disparities
We propose a fair machine learning algorithm to model interpretable differences between observed and desired human decision-making, with the latter aimed at reducing disparity in a downstream outcome impacted by the huma…
Decision MakingLearning Fair Rule Lists
As the use of black-box models becomes ubiquitous in high stake decision-making systems, demands for fair and interpretable models are increasing. While it has been shown that interpretable models can be as accurate as b…
ClassificationDecision MakingFairnessGeneral ClassificationInterpretable Unified Language Checking
Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their la…
Fact CheckingFairnessHate Speech DetectionMisinformationFairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization
Deep learning models often produce performance disparities across demographic groups, due to the training data imbalance with respect to sensitive attributes such as gender or age. To address this problem, existing work …
Representation Learning