Leave-one-out Unfairness

• URL: http://arxiv.org/abs/2107.10171v1
• Date: Wed, 21 Jul 2021 15:55:49 GMT
• Title: Leave-one-out Unfairness
• Authors: Emily Black, Matt Fredrikson
• Abstract summary: We introduce leave-one-out unfairness, which characterizes how likely a model's prediction for an individual will change due to the inclusion or removal of a single other person in the model's training data. We characterize the extent to which deep models behave leave-one-out unfairly on real data, including in cases where the generalization error is small. We discuss salient practical applications that may be negatively affected by leave-one-out unfairness.
• Score: 17.221751674951562
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce leave-one-out unfairness, which characterizes how likely a model's prediction for an individual will change due to the inclusion or removal of a single other person in the model's training data. Leave-one-out unfairness appeals to the idea that fair decisions are not arbitrary: they should not be based on the chance event of any one person's inclusion in the training data. Leave-one-out unfairness is closely related to algorithmic stability, but it focuses on the consistency of an individual point's prediction outcome over unit changes to the training data, rather than the error of the model in aggregate. Beyond formalizing leave-one-out unfairness, we characterize the extent to which deep models behave leave-one-out unfairly on real data, including in cases where the generalization error is small. Further, we demonstrate that adversarial training and randomized smoothing techniques have opposite effects on leave-one-out fairness, which sheds light on the relationships between robustness, memorization, individual fairness, and leave-one-out fairness in deep models. Finally, we discuss salient practical applications that may be negatively affected by leave-one-out unfairness.

Related papers

• Towards Harmless Rawlsian Fairness Regardless of Demographic Prior [57.30787578956235]
  We explore the potential for achieving fairness without compromising its utility when no prior demographics are provided to the training set. We propose a simple but effective method named VFair to minimize the variance of training losses inside the optimal set of empirical losses.
  arXiv  Detail & Related papers  (2024-11-04T12:40:34Z)
• Attacks on fairness in Federated Learning [1.03590082373586]
  We present a new type of attack that compromises the fairness of a trained model. We find that by employing a threat model similar to that of a backdoor attack, an attacker is able to influence the aggregated model to have an unfair performance distribution.
  arXiv  Detail & Related papers  (2023-11-21T16:42:03Z)
• Learning for Counterfactual Fairness from Observational Data [62.43249746968616]
  Fairness-aware machine learning aims to eliminate biases of learning models against certain subgroups described by certain protected (sensitive) attributes such as race, gender, and age. A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data. In this work, we address the problem of counterfactually fair prediction from observational data without given causal models by proposing a novel framework CLAIRE.
  arXiv  Detail & Related papers  (2023-07-17T04:08:29Z)
• On the Cause of Unfairness: A Training Sample Perspective [13.258569961897907]
  We look into the problem through the lens of training data - the major source of unfairness. We quantify the influence of training samples on unfairness by counterfactually changing samples based on predefined concepts. Our framework not only can help practitioners understand the observed unfairness and mitigate it by repairing their training data, but also leads to many other applications.
  arXiv  Detail & Related papers  (2023-06-30T17:48:19Z)
• Revealing Unfair Models by Mining Interpretable Evidence [50.48264727620845]
  The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications. In this paper, we tackle the novel task of revealing unfair models by mining interpretable evidence. Our method finds highly interpretable and solid evidence to effectively reveal the unfairness of trained models.
  arXiv  Detail & Related papers  (2022-07-12T20:03:08Z)
• Agree to Disagree: Diversity through Disagreement for Better Transferability [54.308327969778155]
  We propose D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data. We show how D-BAT naturally emerges from the notion of generalized discrepancy.
  arXiv  Detail & Related papers  (2022-02-09T12:03:02Z)
• Representative & Fair Synthetic Data [68.8204255655161]
  We present a framework to incorporate fairness constraints into the self-supervised learning process. We generate a representative as well as fair version of the UCI Adult census data set. We consider representative & fair synthetic data a promising future building block to teach algorithms not on historic worlds, but rather on the worlds that we strive to live in.
  arXiv  Detail & Related papers  (2021-04-07T09:19:46Z)
• Explainability for fair machine learning [10.227479910430866]
  We present a new approach to explaining fairness in machine learning, based on the Shapley value paradigm. Our fairness explanations attribute a model's overall unfairness to individual input features, even in cases where the model does not operate on sensitive attributes directly. We propose a meta algorithm for applying existing training-time fairness interventions, wherein one trains a perturbation to the original model, rather than a new model entirely.
  arXiv  Detail & Related papers  (2020-10-14T20:21:01Z)
• Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination [53.3082498402884]
  A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. We present a framework of fair semi-supervised learning in the pre-processing phase, including pseudo labeling to predict labels for unlabeled data. A theoretical decomposition analysis of bias, variance and noise highlights the different sources of discrimination and the impact they have on fairness in semi-supervised learning.
  arXiv  Detail & Related papers  (2020-09-25T05:48:56Z)
• Adversarial Learning for Counterfactual Fairness [15.302633901803526]
  In recent years, fairness has become an important topic in the machine learning research community. We propose to rely on an adversarial neural learning approach, that enables more powerful inference than with MMD penalties. Experiments show significant improvements in term of counterfactual fairness for both the discrete and the continuous settings.
  arXiv  Detail & Related papers  (2020-08-30T09:06:03Z)
• Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint [31.86959207229775]
  In this paper, we propose a framework for learning an individually fair classifier. We define the it probability of individual unfairness (PIU) and solve an optimization problem where PIU's upper bound, which can be estimated from data, is controlled to be close to zero. Experimental results show that our method can learn an individually fair classifier at a slight cost of accuracy.
  arXiv  Detail & Related papers  (2020-02-17T02:46:17Z)

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.