Fair Inputs and Fair Outputs: The Incompatibility of Fairness in Privacy and Accuracy
Fairness concerns about algorithmic decision-making systems have been mainly focused on the outputs (e.g., the accuracy of a classifier across individuals or groups). However, one may additionally be concerned with fairness in the inputs. In this paper, we propose and formulate two properties regarding the inputs of (features used by) a classifier. In particular, we claim that fair privacy (whether individuals are all asked to reveal the same information) and need-to-know (whether users are only asked for the minimal information required for the task at hand) are desirable properties of a decision system. We explore the interaction between these properties and fairness in the outputs (fair prediction accuracy). We show that for an optimal classifier these three properties are in general incompatible, and we explain what common properties of data make them incompatible. Finally we provide an algorithm to verify if the trade-off between the three properties exists in a given dataset, and use the algorithm to show that this trade-off is common in real data.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingFairnessSimilar Papers 제목 키워드 기반
LUCID-GAN: Conditional Generative Models to Locate Unfairness
Most group fairness notions detect unethical biases by computing statistical parity metrics on a model's output. However, this approach suffers from several shortcomings, such as philosophical disagreement, mutual incomp…
Bias DetectionFairnessAstraea: Grammar-based Fairness Testing
Software often produces biased outputs. In particular, machine learning (ML) based software are known to produce erroneous predictions when processing discriminatory inputs. Such unfair program behavior can be caused by …
FairnessFault DiagnosisFairness in Contextual Resource Allocation Systems: Metrics and Incompatibility Results
We study critical systems that allocate scarce resources to satisfy basic needs, such as homeless services that provide housing. These systems often support communities disproportionately affected by systemic racial, gen…
counterfactualFairnessFairness and Friends
Recent interest in codifying fairness in Automated Decision Systems (ADS) has resulted in a wide range of formulations of what it means for an algorithm to be “fair.” Most of these propositions are inspired by, but inade…
FairnessPhilosophyTraining Fair Tabular Foundation Models
Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training. Despite the increased use of TFMs in hi…