On the Cause of Unfairness: A Training Sample Perspective

• URL: http://arxiv.org/abs/2306.17828v2
• Date: Fri, 16 Feb 2024 20:20:53 GMT
• Title: On the Cause of Unfairness: A Training Sample Perspective
• Authors: Yuanshun Yao, Yang Liu
• Abstract summary: 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.
• Score: 13.258569961897907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unfairness. We ask the following questions: How would the unfairness of a model change if its training samples (1) were collected from a different (e.g. demographic) group, (2) were labeled differently, or (3) whose features were modified? In other words, we quantify the influence of training samples on unfairness by counterfactually changing samples based on predefined concepts, i.e. data attributes such as features, labels, and sensitive attributes. 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, e.g. detecting mislabeling, fixing imbalanced representations, and detecting fairness-targeted poisoning attacks.

Related papers

• Fair Few-shot Learning with Auxiliary Sets [53.30014767684218]
  In many machine learning (ML) tasks, only very few labeled data samples can be collected, which can lead to inferior fairness performance. In this paper, we define the fairness-aware learning task with limited training samples as the emphfair few-shot learning problem. We devise a novel framework that accumulates fairness-aware knowledge across different meta-training tasks and then generalizes the learned knowledge to meta-test tasks.
  arXiv  Detail & Related papers  (2023-08-28T06:31:37Z)
• FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification [14.589159162086926]
  We propose FairAdaBN, which makes batch normalization adaptive to sensitive attribute. We propose a new metric, named Fairness-Accuracy Trade-off Efficiency (FATE), to compute normalized fairness improvement over accuracy drop. Experiments on two dermatological datasets show that our proposed method outperforms other methods on fairness criteria and FATE.
  arXiv  Detail & Related papers  (2023-03-15T02:22:07Z)
• 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)
• 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)
• On Disentangled and Locally Fair Representations [95.6635227371479]
  We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. We learn a locally fair representation, such that, under the learned representation, the neighborhood of each sample is balanced in terms of the sensitive attribute.
  arXiv  Detail & Related papers  (2022-05-05T14:26:50Z)
• FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes [51.02407217197623]
  We propose a two-stage training algorithm named FAIRIF. It minimizes the loss over the reweighted data set where the sample weights are computed. We show that FAIRIF yields models with better fairness-utility trade-offs against various types of bias.
  arXiv  Detail & Related papers  (2022-01-15T05:14:48Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)
• Leave-one-out Unfairness [17.221751674951562]
  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.
  arXiv  Detail & Related papers  (2021-07-21T15:55:49Z)
• 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)
• Unfairness Discovery and Prevention For Few-Shot Regression [9.95899391250129]
  We study fairness in supervised few-shot meta-learning models sensitive to discrimination (or bias) in historical data. A machine learning model trained based on biased data tends to make unfair predictions for users from minority groups.
  arXiv  Detail & Related papers  (2020-09-23T22:34:06Z)

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.