When mitigating bias is unfair: multiplicity and arbitrariness in algorithmic group fairness

• URL: http://arxiv.org/abs/2302.07185v2
• Date: Wed, 22 May 2024 09:07:20 GMT
• Title: When mitigating bias is unfair: multiplicity and arbitrariness in algorithmic group fairness
• Authors: Natasa Krco, Thibault Laugel, Vincent Grari, Jean-Michel Loubes, Marcin Detyniecki,
• Abstract summary: We introduce the FRAME (FaiRness Arbitrariness and Multiplicity Evaluation) framework, which evaluates bias mitigation through five dimensions. Applying FRAME to various bias mitigation approaches across key datasets allows us to exhibit significant differences in the behaviors of debiasing methods. These findings highlight the limitations of current fairness criteria and the inherent arbitrariness in the debiasing process.
• Score: 8.367620276482056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most research on fair machine learning has prioritized optimizing criteria such as Demographic Parity and Equalized Odds. Despite these efforts, there remains a limited understanding of how different bias mitigation strategies affect individual predictions and whether they introduce arbitrariness into the debiasing process. This paper addresses these gaps by exploring whether models that achieve comparable fairness and accuracy metrics impact the same individuals and mitigate bias in a consistent manner. We introduce the FRAME (FaiRness Arbitrariness and Multiplicity Evaluation) framework, which evaluates bias mitigation through five dimensions: Impact Size (how many people were affected), Change Direction (positive versus negative changes), Decision Rates (impact on models' acceptance rates), Affected Subpopulations (who was affected), and Neglected Subpopulations (where unfairness persists). This framework is intended to help practitioners understand the impacts of debiasing processes and make better-informed decisions regarding model selection. Applying FRAME to various bias mitigation approaches across key datasets allows us to exhibit significant differences in the behaviors of debiasing methods. These findings highlight the limitations of current fairness criteria and the inherent arbitrariness in the debiasing process.

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)
• How to be fair? A study of label and selection bias [3.018638214344819]
  It is widely accepted that biased data leads to biased and potentially unfair models. Several measures for bias in data and model predictions have been proposed, as well as bias mitigation techniques. Despite the myriad of mitigation techniques developed in the past decade, it is still poorly understood under what circumstances which methods work.
  arXiv  Detail & Related papers  (2024-03-21T10:43:55Z)
• Explaining Knock-on Effects of Bias Mitigation [13.46387356280467]
  In machine learning systems, bias mitigation approaches aim to make outcomes fairer across privileged and unprivileged groups. In this paper, we aim to characterise impacted cohorts when mitigation interventions are applied. We examine a range of bias mitigation strategies that work at various stages of the model life cycle. We show that all tested mitigation strategies negatively impact a non-trivial fraction of cases, i.e., people who receive unfavourable outcomes solely on account of mitigation efforts.
  arXiv  Detail & Related papers  (2023-12-01T18:40:37Z)
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)
• Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP [64.45845091719002]
  Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. This paper seeks to clarify the current situation and plot a course for meaningful progress in fair learning.
  arXiv  Detail & Related papers  (2023-02-11T14:54:00Z)
• Systematic Evaluation of Predictive Fairness [60.0947291284978]
  Mitigating bias in training on biased datasets is an important open problem. We examine the performance of various debiasing methods across multiple tasks. We find that data conditions have a strong influence on relative model performance.
  arXiv  Detail & Related papers  (2022-10-17T05:40:13Z)
• Survey on Fairness Notions and Related Tensions [4.257210316104905]
  Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting. However, objective machine learning (ML) algorithms are prone to bias, which results in yet unfair decisions. This paper surveys the commonly used fairness notions and discusses the tensions among them with privacy and accuracy.
  arXiv  Detail & Related papers  (2022-09-16T13:36:05Z)
• Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity [10.144058870887061]
  We argue that individuals can be harmed when one predictor is chosen ad hoc from a group of equally well performing models. Our findings suggest that such unfairness can be readily found in real life and it may be difficult to mitigate by technical means alone.
  arXiv  Detail & Related papers  (2022-03-14T14:33:39Z)
• Information-Theoretic Bias Reduction via Causal View of Spurious Correlation [71.9123886505321]
  We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation. We present a novel debiasing framework against the algorithmic bias, which incorporates a bias regularization loss. The proposed bias measurement and debiasing approaches are validated in diverse realistic scenarios.
  arXiv  Detail & Related papers  (2022-01-10T01:19:31Z)
• One-vs.-One Mitigation of Intersectional Bias: A General Method to Extend Fairness-Aware Binary Classification [0.48733623015338234]
  One-vs.-One Mitigation is a process of comparison between each pair of subgroups related to sensitive attributes to the fairness-aware machine learning for binary classification. Our method mitigates the intersectional bias much better than conventional methods in all the settings.
  arXiv  Detail & Related papers  (2020-10-26T11:35:39Z)

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.