SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
In this paper, we cast fair machine learning as invariant machine learning. We first formulate a version of individual fairness that enforces invariance on certain sensitive sets. We then design a transport-based regularizer that enforces this version of individual fairness and develop an algorithm to minimize the regularizer efficiently. Our theoretical results guarantee the proposed approach trains certifiably fair ML models. Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are susceptible to algorithmic bias.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningFairnessSimilar Papers 제목 키워드 기반
Causal Manifold Fairness: Enforcing Geometric Invariance in Representation Learning
Fairness in machine learning is increasingly critical, yet standard approaches often treat data as static points in a high-dimensional space, ignoring the underlying generative structure. We posit that sensitive attribut…
Representation LearningCausal InferenceFairness by Learning Orthogonal Disentangled Representations
Learning discriminative powerful representations is a crucial step for machine learning systems. Introducing invariance against arbitrary nuisance or sensitive attributes while performing well on specific tasks is an imp…
DisentanglementFairnessRepresentation LearningEiFFFeL: Enforcing Fairness in Forests by Flipping Leaves
Nowadays Machine Learning (ML) techniques are extensively adopted in many socially sensitive systems, thus requiring to carefully study the fairness of the decisions taken by such systems. Many approaches have been propo…
FairnessSENSEi: Input-Sensitive Compilation for Accelerating GNNs
Over the years, many frameworks and optimization techniques have been proposed to accelerate graph neural networks (GNNs). Compared to the optimizations explored in these systems, we observe that different matrix re-asso…
Graph AttentionGraph EmbeddingTaking Advantage of Multitask Learning for Fair Classification
A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information (e.g., gender or ethnic group) as part o…
ClassificationDecision MakingFairnessGeneral Classification