A Primer on Causal and Statistical Dataset Biases for Fair and Robust Image Analysis
Machine learning methods often fail when deployed in the real world. Worse still, they fail in high-stakes situations and across socially sensitive lines. These issues have a chilling effect on the adoption of machine learning methods in settings such as medical diagnosis, where they are arguably best-placed to provide benefits if safely deployed. In this primer, we introduce the causal and statistical structures which induce failure in machine learning methods for image analysis. We highlight two previously overlooked problems, which we call the \textit{no fair lunch} problem and the \textit{subgroup separability} problem. We elucidate why today's fair representation learning methods fail to adequately solve them and propose potential paths forward for the field.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningMedical DiagnosisSimilar Papers 제목 키워드 기반
The Impossibility Theorem of Machine Fairness -- A Causal Perspective
With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exi…
FairnessEnhancing Model Robustness and Fairness with Causality: A Regularization Approach
Recent work has raised concerns on the risk of spurious correlations and unintended biases in statistical machine learning models that threaten model robustness and fairness. In this paper, we propose a simple and intuit…
Causal InferencecounterfactualFairnessRethinking Fair Representation Learning for Performance-Sensitive Tasks
We investigate the prominent class of fair representation learning methods for bias mitigation. Using causal reasoning to define and formalise different sources of dataset bias, we reveal important implicit assumptions i…
Representation LearningThe 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…
FairnessInformativenessSensitivityFair Clustering: A Causal Perspective
Clustering algorithms may unintentionally propagate or intensify existing disparities, leading to unfair representations or biased decision-making. Current fair clustering methods rely on notions of fairness that do not …
ClusteringDecision MakingFairness