Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate

• URL: http://arxiv.org/abs/2309.03426v3
• Date: Tue, 28 May 2024 15:55:36 GMT
• Title: Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
• Authors: Yuancheng Xu, Chenghao Deng, Yanchao Sun, Ruijie Zheng, Xiyao Wang, Jieyu Zhao, Furong Huang,
• Abstract summary: We introduce a long-term fairness concept named Equal Long-term Benefit Rate (ELBERT) to address biases in sequential decision-making. ELBERT effectively addresses the temporal discrimination issues found in previous long-term fairness notions. We show that ELBERT-PO significantly diminishes bias while maintaining high utility.
• Score: 41.51680686036846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decisions made by machine learning models can have lasting impacts, making long-term fairness a critical consideration. It has been observed that ignoring the long-term effect and directly applying fairness criterion in static settings can actually worsen bias over time. To address biases in sequential decision-making, we introduce a long-term fairness concept named Equal Long-term Benefit Rate (ELBERT). This concept is seamlessly integrated into a Markov Decision Process (MDP) to consider the future effects of actions on long-term fairness, thus providing a unified framework for fair sequential decision-making problems. ELBERT effectively addresses the temporal discrimination issues found in previous long-term fairness notions. Additionally, we demonstrate that the policy gradient of Long-term Benefit Rate can be analytically simplified to standard policy gradients. This simplification makes conventional policy optimization methods viable for reducing bias, leading to our bias mitigation approach ELBERT-PO. Extensive experiments across various diverse sequential decision-making environments consistently reveal that ELBERT-PO significantly diminishes bias while maintaining high utility. Code is available at https://github.com/umd-huang-lab/ELBERT.

Related papers

• Editable Fairness: Fine-Grained Bias Mitigation in Language Models [52.66450426729818]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases. FAST surpasses state-of-the-art baselines with superior debiasing performance. This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Fairness-Accuracy Trade-Offs: A Causal Perspective [58.06306331390586]
  We analyze the tension between fairness and accuracy from a causal lens for the first time. We show that enforcing a causal constraint often reduces the disparity between demographic groups. We introduce a new neural approach for causally-constrained fair learning.
  arXiv  Detail & Related papers  (2024-05-24T11:19:52Z)
• Policy Learning for Balancing Short-Term and Long-Term Rewards [11.859587700058235]
  This paper formalizes a new framework for learning the optimal policy, where some long-term outcomes are allowed to be missing. We show that short-term outcomes, if associated, contribute to improving the estimator of the long-term reward balances.
  arXiv  Detail & Related papers  (2024-05-06T10:09:35Z)
• Equal Opportunity of Coverage in Fair Regression [50.76908018786335]
  We study fair machine learning (ML) under predictive uncertainty to enable reliable and trustworthy decision-making. We propose Equal Opportunity of Coverage (EOC) that aims to achieve two properties: (1) coverage rates for different groups with similar outcomes are close, and (2) the coverage rate for the entire population remains at a predetermined level.
  arXiv  Detail & Related papers  (2023-11-03T21:19:59Z)
• Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems [14.095401339355677]
  Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate decision-making with long-term fairness requirements. We show that policy optimization methods from deep reinforcement learning can be used to find strictly better decision policies.
  arXiv  Detail & Related papers  (2022-10-22T20:41:36Z)
• Enforcing Delayed-Impact Fairness Guarantees [21.368958668652652]
  We introduce ELF, the first classification algorithm that provides high-confidence fairness guarantees in terms of long-term, or delayed, impact. We show experimentally that our algorithm can successfully mitigate long-term unfairness.
  arXiv  Detail & Related papers  (2022-08-24T19:14:56Z)
• Achieving Long-Term Fairness in Sequential Decision Making [9.046461405943502]
  We propose a framework for achieving long-term fair sequential decision making. We take path-specific effects on the time-lagged causal graph as a quantitative tool for measuring long-term fairness.
  arXiv  Detail & Related papers  (2022-04-04T20:05:44Z)
• State-Visitation Fairness in Average-Reward MDPs [5.190207094732672]
  We study fairness in temporally extended decision-making settings, specifically those formulated as Markov Decision Processes (MDPs) Our proposed notion of fairness ensures that each state's long-term visitation frequency is more than a specified fraction. The proposed solution guarantees a simultaneous approximation on the expected average-reward and the long-term state-visitation frequency.
  arXiv  Detail & Related papers  (2021-02-14T10:20:53Z)
• Provably Good Batch Reinforcement Learning Without Great Exploration [51.51462608429621]
  Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Recent algorithms have shown promise but can still be overly optimistic in their expected outcomes. We show that a small modification to Bellman optimality and evaluation back-up to take a more conservative update can have much stronger guarantees.
  arXiv  Detail & Related papers  (2020-07-16T09:25:54Z)
• Algorithmic Decision Making with Conditional Fairness [48.76267073341723]
  We define conditional fairness as a more sound fairness metric by conditioning on the fairness variables. We propose a Derivable Conditional Fairness Regularizer (DCFR) to track the trade-off between precision and fairness of algorithmic decision making.
  arXiv  Detail & Related papers  (2020-06-18T12:56:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.