Implementing Fairness in AI Classification: The Role of Explainability

• URL: http://arxiv.org/abs/2407.14766v2
• Date: Mon, 24 Mar 2025 05:27:33 GMT
• Title: Implementing Fairness in AI Classification: The Role of Explainability
• Authors: Thomas Souverain, Johnathan Nguyen, Nicolas Meric, Paul Égré,
• Abstract summary: We argue that implementing fairness in AI classification involves more work than just operationalizing a fairness metric.<n>We make the training processes transparent, determining what outcomes the fairness criteria actually produce, and assessing their trade-offs.<n>We draw conclusions regarding the way in which these explanatory steps can make an AI model trustworthy.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a philosophical and experimental investigation of the problem of AI fairness in classification. We argue that implementing fairness in AI classification involves more work than just operationalizing a fairness metric. It requires establishing the explainability of the classification model chosen and of the principles behind it. Specifically, it involves making the training processes transparent, determining what outcomes the fairness criteria actually produce, and assessing their trade-offs by comparison with closely related models that would lead to a different outcome. To exemplify this methodology, we trained a model and developed a tool for disparity detection and fairness interventions, the package FairDream. While FairDream is set to enforce Demographic Parity, experiments reveal that it fulfills the constraint of Equalized Odds. The algorithm is thus more conservative than the user might expect. To justify this outcome, we first clarify the relation between Demographic Parity and Equalized Odds as fairness criteria. We then explain FairDream's reweighting method and justify the trade-offs reached by FairDream by a benchmark comparison with closely related GridSearch models. We draw conclusions regarding the way in which these explanatory steps can make an AI model trustworthy.

Related papers

• Learning Counterfactually Fair Models via Improved Generation with Neural Causal Models [0.0]
  One of the main concerns while deploying machine learning models in real-world applications is fairness. Existing methodologies for enforcing counterfactual fairness seem to have two limitations. We propose employing Neural Causal Models for generating the counterfactual samples. We also propose a new MMD-based regularizer term that explicitly enforces the counterfactual fairness conditions into the base model while training.
  arXiv  Detail & Related papers  (2025-02-18T11:59:03Z)
• What's Distributive Justice Got to Do with It? Rethinking Algorithmic Fairness from the Perspective of Approximate Justice [1.8434042562191815]
  We argue that in the context of imperfect decision-making systems, we should not only care about what the ideal distribution of benefits/harms among individuals would look like. This requires us to rethink the way in which we, as algorithmic fairness researchers, view distributive justice and use fairness criteria.
  arXiv  Detail & Related papers  (2024-07-17T11:13:23Z)
• 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)
• Classes Are Not Equal: An Empirical Study on Image Recognition Fairness [100.36114135663836]
  We experimentally demonstrate that classes are not equal and the fairness issue is prevalent for image classification models across various datasets. Our findings reveal that models tend to exhibit greater prediction biases for classes that are more challenging to recognize. Data augmentation and representation learning algorithms improve overall performance by promoting fairness to some degree in image classification.
  arXiv  Detail & Related papers  (2024-02-28T07:54:50Z)
• Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness [15.83823345486604]
  We motivatefactual fairness by showing that there is not a fundamental trade-off between fairness and accuracy. Counterfactual fairness can sometimes be tested by measuring relatively simple group fairness metrics.
  arXiv  Detail & Related papers  (2023-10-30T16:07:57Z)
• 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)
• 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)
• Causal Fair Machine Learning via Rank-Preserving Interventional Distributions [0.5062312533373299]
  We define individuals as being normatively equal if they are equal in a fictitious, normatively desired (FiND) world. We propose rank-preserving interventional distributions to define a specific FiND world in which this holds. We show that our warping approach effectively identifies the most discriminated individuals and mitigates unfairness.
  arXiv  Detail & Related papers  (2023-07-24T13:46:50Z)
• 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)
• 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)
• 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)
• Counterfactual Fairness Is Basically Demographic Parity [0.0]
  Making fair decisions is crucial to ethically implementing machine learning algorithms in social settings. We show that an algorithm which satisfies counterfactual fairness also satisfies demographic parity. We formalize a concrete fairness goal: to preserve the order of individuals within protected groups.
  arXiv  Detail & Related papers  (2022-08-07T23:38:59Z)
• 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)
• How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts [107.72786199113183]
  We propose a novel fairness learning method termed CUrvature MAtching (CUMA) CUMA achieves robust fairness generalizable to unseen domains with unknown distributional shifts. We evaluate our method on three popular fairness datasets.
  arXiv  Detail & Related papers  (2022-07-04T02:37:50Z)
• 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)
• Measuring Fairness of Text Classifiers via Prediction Sensitivity [63.56554964580627]
  ACCUMULATED PREDICTION SENSITIVITY measures fairness in machine learning models based on the model's prediction sensitivity to perturbations in input features. We show that the metric can be theoretically linked with a specific notion of group fairness (statistical parity) and individual fairness.
  arXiv  Detail & Related papers  (2022-03-16T15:00:33Z)
• Are There Exceptions to Goodhart's Law? On the Moral Justification of Fairness-Aware Machine Learning [14.428360876120333]
  We argue that fairness measures are particularly sensitive to Goodhart's law. We present a framework for moral reasoning about the justification of fairness metrics.
  arXiv  Detail & Related papers  (2022-02-17T09:26:39Z)
• Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks [17.231251035416648]
  We study whether fair representation can be used to guarantee fairness for unknown tasks and for multiple fairness notions simultaneously. We prove that, although fair representation might not guarantee fairness for all prediction tasks, it does guarantee fairness for an important subset of tasks.
  arXiv  Detail & Related papers  (2021-09-01T17:29:11Z)
• 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)
• Convex Fairness Constrained Model Using Causal Effect Estimators [6.414055487487486]
  We devise novel models, called FairCEEs, which remove discrimination while keeping explanatory bias. We provide an efficient algorithm for solving FairCEEs in regression and binary classification tasks.
  arXiv  Detail & Related papers  (2020-02-16T03:40:04Z)

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.