Beyond traditional assumptions in fair machine learning
This thesis scrutinizes common assumptions underlying traditional machine learning approaches to fairness in consequential decision making. After challenging the validity of these assumptions in real-world applications, we propose ways to move forward when they are violated. First, we show that group fairness criteria purely based on statistical properties of observed data are fundamentally limited. Revisiting this limitation from a causal viewpoint we develop a more versatile conceptual framework, causal fairness criteria, and first algorithms to achieve them. We also provide tools to analyze how sensitive a believed-to-be causally fair algorithm is to misspecifications of the causal graph. Second, we overcome the assumption that sensitive data is readily available in practice. To this end we devise protocols based on secure multi-party computation to train, validate, and contest fair decision algorithms without requiring users to disclose their sensitive data or decision makers to disclose their models. Finally, we also accommodate the fact that outcome labels are often only observed when a certain decision has been made. We suggest a paradigm shift away from training predictive models towards directly learning decisions to relax the traditional assumption that labels can always be recorded. The main contribution of this thesis is the development of theoretically substantiated and practically feasible methods to move research on fair machine learning closer to real-world applications.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningDecision MakingFairnessSimilar Papers 제목 키워드 기반
Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Research
Across machine learning (ML) sub-disciplines, researchers make explicit mathematical assumptions in order to facilitate proof-writing. We note that, specifically in the area of fairness-accuracy trade-off optimization sc…
BIG-bench Machine LearningFairnessComparing Fair Ranking Metrics
Ranked lists are frequently used by information retrieval (IR) systems to present results believed to be relevant to the users information need. Fairness is a relatively new but important aspect of these rankings to meas…
FairnessInformation RetrievalRecommendation SystemsRetrievalA Reproducibility Study of Product-side Fairness in Bundle Recommendation
Recommender systems are known to exhibit fairness issues, particularly on the product side, where products and their associated suppliers receive unequal exposure in recommended results. While this problem has been widel…
FairnessRecommendation SystemsFairness and Randomness in Machine Learning: Statistical Independence and Relativization
Fair Machine Learning endeavors to prevent unfairness arising in the context of machine learning applications embedded in society. Despite the variety of definitions of fairness and proposed "fair algorithms", there rema…
BIG-bench Machine LearningFairnessThe Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
Fairness metrics are a core tool in the fair machine learning literature (FairML), used to determine that ML models are, in some sense, "fair". Real-world data, however, are typically plagued by various measurement biase…
FairnessInformativenessSensitivity