The Frontiers of Fairness in Machine Learning

Abstract

The last few years have seen an explosion of academic and popular interest in algorithmic fairness. Despite this interest and the volume and velocity of work that has been produced recently, the fundamental science of fairness in machine learning is still in a nascent state. In March 2018, we convened a group of experts as part of a CCC visioning workshop to assess the state of the field, and distill the most promising research directions going forward. This report summarizes the findings of that workshop. Along the way, it surveys recent theoretical work in the field and points towards promising directions for research.

References in corpus (5)

• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• On the (im)possibility of fairness
• Learning Adversarially Fair and Transferable Representations
• Provably Fair Representations
• Fair Personalization

Cited by in corpus (72)

• Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions
• A Comprehensive Survey on Deep Graph Representation Learning
• A Clarification of the Nuances in the Fairness Metrics Landscape
• An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction
• Trustworthy AI and Robotics and the Implications for the AEC Industry: A Systematic Literature Review and Future Potentials
• Understanding Frontline Workers' and Unhoused Individuals' Perspectives on AI Used in Homeless Services
• Keeping Community in the Loop: Understanding Wikipedia Stakeholder Values for Machine Learning-Based Systems
• Fair Regression for Health Care Spending
• Four Years of FAccT: A Reflexive, Mixed-Methods Analysis of Research Contributions, Shortcomings, and Future Prospects
• Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems
• Mitigating Gender Bias in Natural Language Processing: Literature Review
• FairBatch: Batch Selection for Model Fairness
• Individual Fairness for $k$-Clustering
• Factors Influencing Perceived Fairness in Algorithmic Decision-Making: Algorithm Outcomes, Development Procedures, and Individual Differences
• Learning Certified Individually Fair Representations
• Constrained Classification and Policy Learning
• Robustness Disparities in Commercial Face Detection
• Can Explainable AI Explain Unfairness? A Framework for Evaluating Explainable AI
• Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
• A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-${\ell }_1$-Norm Interpolated Classifiers
• Fairness in Streaming Submodular Maximization: Algorithms and Hardness
• Differentially Private Fair Learning
• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
• Conditional Learning of Fair Representations
• Axes for Sociotechnical Inquiry in AI Research
• BeFair: Addressing Fairness in the Banking Sector
• Extending the Machine Learning Abstraction Boundary: A Complex Systems Approach to Incorporate Societal Context
• Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness
• A Center in Your Neighborhood: Fairness in Facility Location
• Counterfactual Reasoning for Fair Clinical Risk Prediction
• Contrastive Examples for Addressing the Tyranny of the Majority
• Environment Inference for Invariant Learning
• Predicting Early Dropout: Calibration and Algorithmic Fairness Considerations
• Approximation Algorithms for Socially Fair Clustering
• Fairness-aware Model-agnostic Positive and Unlabeled Learning
• Statistical Equity: A Fairness Classification Objective
• Learning Fair Rule Lists
• Metric-Free Individual Fairness in Online Learning
• Comparing Human and Machine Bias in Face Recognition
• Fair and Unbiased Algorithmic Decision Making: Current State and Future Challenges
• Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
• Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach
• Group Fairness in Bandit Arm Selection
• Interpretable Learning-to-Rank with Generalized Additive Models
• Fairness and Missing Values
• Improved Approximation Algorithms for Individually Fair Clustering
• Fairness criteria through the lens of directed acyclic graphical models
• Fairness in Missing Data Imputation
• Cohort Shapley value for algorithmic fairness
• Learning Smooth and Fair Representations
• Fair Data Representation for Machine Learning at the Pareto Frontier
• Multi-Differential Fairness Auditor for Black Box Classifiers
• Computability, Complexity, Consistency and Controllability: A Four C's Framework for cross-disciplinary Ethical Algorithm Research
• Learning Fair and Interpretable Representations via Linear Orthogonalization
• Leveraging Administrative Data for Bias Audits: Assessing Disparate Coverage with Mobility Data for COVID-19 Policy
• Quantifying Infra-Marginality and Its Trade-off with Group Fairness
• On the Impact of Data Quality on Image Classification Fairness
• Additive Adversarial Learning for Unbiased Authentication
• Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness
• Metric-Free Individual Fairness with Cooperative Contextual Bandits
• Towards Fair Deep Anomaly Detection
• Unsupervised Learning of Debiased Representations with Pseudo-Attributes
• Fairness-aware Summarization for Justified Decision-Making
• Everything is Relative: Understanding Fairness with Optimal Transport
• A Sociotechnical View of Algorithmic Fairness
• Deep Clustering based Fair Outlier Detection
• Fairness-Aware Unsupervised Feature Selection
• Learning how to approve updates to machine learning algorithms in non-stationary settings
• Individually Fair Gradient Boosting
• On the Identification of Fair Auditors to Evaluate Recommender Systems based on a Novel Non-Comparative Fairness Notion
• Towards Fair Cross-Domain Adaptation via Generative Learning
• Non-Comparative Fairness for Human-Auditing and Its Relation to Traditional Fairness Notions