Utility-Fairness Trade-Offs and How to Find Them

• URL: http://arxiv.org/abs/2404.09454v2
• Date: Wed, 24 Apr 2024 00:08:42 GMT
• Title: Utility-Fairness Trade-Offs and How to Find Them
• Authors: Sepehr Dehdashtian, Bashir Sadeghi, Vishnu Naresh Boddeti,
• Abstract summary: We introduce two utility-fairness trade-offs: the Data-Space and Label-Space Trade-off. We propose U-FaTE, a method to numerically quantify the trade-offs for a given prediction task and group fairness definition from data samples. An extensive evaluation of fair representation learning methods and representations from over 1000 pre-trained models revealed that most current approaches are far from the estimated and achievable fairness-utility trade-offs.
• Score: 14.1278892335105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When building classification systems with demographic fairness considerations, there are two objectives to satisfy: 1) maximizing utility for the specific task and 2) ensuring fairness w.r.t. a known demographic attribute. These objectives often compete, so optimizing both can lead to a trade-off between utility and fairness. While existing works acknowledge the trade-offs and study their limits, two questions remain unanswered: 1) What are the optimal trade-offs between utility and fairness? and 2) How can we numerically quantify these trade-offs from data for a desired prediction task and demographic attribute of interest? This paper addresses these questions. We introduce two utility-fairness trade-offs: the Data-Space and Label-Space Trade-off. The trade-offs reveal three regions within the utility-fairness plane, delineating what is fully and partially possible and impossible. We propose U-FaTE, a method to numerically quantify the trade-offs for a given prediction task and group fairness definition from data samples. Based on the trade-offs, we introduce a new scheme for evaluating representations. An extensive evaluation of fair representation learning methods and representations from over 1000 pre-trained models revealed that most current approaches are far from the estimated and achievable fairness-utility trade-offs across multiple datasets and prediction tasks.

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)
• A Benchmark for Fairness-Aware Graph Learning [58.515305543487386]
  We present an extensive benchmark on ten representative fairness-aware graph learning methods. Our in-depth analysis reveals key insights into the strengths and limitations of existing methods.
  arXiv  Detail & Related papers  (2024-07-16T18:43:43Z)
• Trusting Fair Data: Leveraging Quality in Fairness-Driven Data Removal Techniques [0.0]
  We deal with bias mitigation techniques that remove specific data points from the training set to aim for a fair representation of the population. We propose additional requirements and objectives that the subsets must fulfill in addition to fairness.
  arXiv  Detail & Related papers  (2024-05-21T16:51:28Z)
• A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier [42.18013955576355]
  The accuracy-fairness trade-off has been frequently observed in the literature of fair machine learning. This work seeks to develop a theoretical framework by characterizing the shape of the accuracy-fairness trade-off. The proposed research enables an in-depth understanding of the accuracy-fairness trade-off, pushing current fair machine-learning research to a new frontier.
  arXiv  Detail & Related papers  (2023-10-19T14:35:26Z)
• 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)
• 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)
• Fairness Explainability using Optimal Transport with Applications in Image Classification [0.46040036610482665]
  We propose a comprehensive approach to uncover the causes of discrimination in Machine Learning applications. We leverage Wasserstein barycenters to achieve fair predictions and introduce an extension to pinpoint bias-associated regions. This allows us to derive a cohesive system which uses the enforced fairness to measure each features influence emphon the bias.
  arXiv  Detail & Related papers  (2023-08-22T00:10:23Z)
• DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision [73.80009454050858]
  This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Our model jointly optimize for two fairness criteria - group fairness and counterfactual fairness.
  arXiv  Detail & Related papers  (2023-03-15T07:13:54Z)
• Impossibility results for fair representations [12.483260526189447]
  We argue that no representation can guarantee the fairness of classifiers for different tasks trained using it. More refined notions of fairness, like Odds Equality, cannot be guaranteed by a representation that does not take into account the task specific labeling rule.
  arXiv  Detail & Related papers  (2021-07-07T21:12:55Z)
• 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)
• Machine learning fairness notions: Bridging the gap with real-world applications [4.157415305926584]
  Fairness emerged as an important requirement to guarantee that Machine Learning predictive systems do not discriminate against specific individuals or entire sub-populations. This paper is a survey that illustrates the subtleties between fairness notions through a large number of examples and scenarios.
  arXiv  Detail & Related papers  (2020-06-30T13:01:06Z)

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.