Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness

• URL: http://arxiv.org/abs/2202.10816v2
• Date: Wed, 23 Feb 2022 10:47:03 GMT
• Title: Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness
• Authors: Carolyn Ashurst, Ryan Carey, Silvia Chiappa, Tom Everitt
• Abstract summary: In addition to reproducing discriminatory relationships in the training data, machine learning systems can also introduce or amplify discriminatory effects. We refer to this as introduced unfairness, and investigate the conditions under which it may arise. We propose introduced total variation as a measure of introduced unfairness, and establish graphical conditions under which it may be incentivised to occur.
• Score: 14.710365964629066
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In addition to reproducing discriminatory relationships in the training data, machine learning systems can also introduce or amplify discriminatory effects. We refer to this as introduced unfairness, and investigate the conditions under which it may arise. To this end, we propose introduced total variation as a measure of introduced unfairness, and establish graphical conditions under which it may be incentivised to occur. These criteria imply that adding the sensitive attribute as a feature removes the incentive for introduced variation under well-behaved loss functions. Additionally, taking a causal perspective, introduced path-specific effects shed light on the issue of when specific paths should be considered fair.

Related papers

• 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)
• What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning [52.51430732904994]
  In reinforcement learning problems, agents must consider long-term fairness while maximizing returns. Recent works have proposed many different types of fairness notions, but how unfairness arises in RL problems remains unclear. We introduce a novel notion called dynamics fairness, which explicitly captures the inequality stemming from environmental dynamics.
  arXiv  Detail & Related papers  (2024-04-16T22:47:59Z)
• Understanding Instance-Level Impact of Fairness Constraints [12.866655972682254]
  We study the influence of training examples when fairness constraints are imposed. We find that training on a subset of weighty data examples leads to lower fairness violations with a trade-off of accuracy.
  arXiv  Detail & Related papers  (2022-06-30T17:31:33Z)
• Counterfactual Fairness with Partially Known Causal Graph [85.15766086381352]
  This paper proposes a general method to achieve the notion of counterfactual fairness when the true causal graph is unknown. We find that counterfactual fairness can be achieved as if the true causal graph were fully known, when specific background knowledge is provided.
  arXiv  Detail & Related papers  (2022-05-27T13:40:50Z)
• Learning Fair Node Representations with Graph Counterfactual Fairness [56.32231787113689]
  We propose graph counterfactual fairness, which considers the biases led by the above facts. We generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes. Our framework outperforms the state-of-the-art baselines in graph counterfactual fairness.
  arXiv  Detail & Related papers  (2022-01-10T21:43:44Z)
• Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer [72.5190560787569]
  In computer vision, learning from long tailed datasets is a recurring theme, especially for natural image datasets. Our proposal posits a meta-distributional scenario, where the data generating mechanism is invariant across the label-conditional feature distributions. This allows us to leverage a causal data inflation procedure to enlarge the representation of minority classes.
  arXiv  Detail & Related papers  (2020-11-25T00:13:11Z)
• Shortcomings of Counterfactual Fairness and a Proposed Modification [0.0]
  I argue that counterfactual fairness does not constitute a necessary condition for an algorithm to be fair. I then suggest how the constraint can be modified in order to remedy this shortcoming.
  arXiv  Detail & Related papers  (2020-11-14T14:49:51Z)
• On the Fairness of Causal Algorithmic Recourse [36.519629650529666]
  We propose two new fairness criteria at the group and individual level. We show that fairness of recourse is complementary to fairness of prediction. We discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions.
  arXiv  Detail & Related papers  (2020-10-13T16:35:06Z)
• 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.