Algorithmic Fairness Over Time: Advances & Prospects
cs.LG
Submitted: 2026-10-10
Updated: 2026-10-10
Comments: Accepted at EWAF 2024, unpublished
Code: https://github.com/propublica/compas-analysis
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: In the presence of feedback loops, algorithmic decisions at one time step can influence observed data in subsequent steps, potentially introducing selection bias or shifts in data distribution.
Abstract
In the presence of feedback loops, algorithmic decisions at one time step can influence observed data in subsequent steps, potentially introducing selection bias or shifts in data distribution. Research has demonstrated that ignoring these effects can lead to unfairness, which may worsen over time as the model remains deployed within society. This raises important questions of how to measure and ensure fairness of algorithmic decision-making models over time. In this short paper, we present a taxonomy that distinguishes between different types of static and temporal fairness notions in recent advancements. We then suggest prospects for future research by identifying common implicit temporal assumptions, open questions to enhance our temporal understanding of fairness, and other open challenges.
Sources
- A statistical framework for fair predictive algorithms
- A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems
- On Prediction-Modelers and Decision-Makers: Why Fairness Requires More Than a Fair Prediction Model
- The Frontiers of Fairness in Machine Learning
- Designing Long-term Group Fair Policies in Dynamical Systems
- Enforcing Delayed-Impact Fairness Guarantees
- FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systems
- Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
- Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
- Equalizing Recourse across Groups
- The Curse of Recursion: Training on Generated Data Makes Models Forget
- Bias and Fairness in Large Language Models: A Survey
- Fairness of ChatGPT
- FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks