Fair Text Classification via Transferable Representations

• URL: http://arxiv.org/abs/2503.07691v1
• Date: Mon, 10 Mar 2025 16:52:45 GMT
• Title: Fair Text Classification via Transferable Representations
• Authors: Thibaud Leteno, Michael Perrot, Charlotte Laclau, Antoine Gourru, Christophe Gravier,
• Abstract summary: Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups remains an open challenge.<n>We propose an approach that extends the use of the Wasserstein Dependency Measure for learning unbiased neural text classifiers.<n>We show that Domain Adaptation can be efficiently leveraged to remove the need for access to the sensitive attributes in the dataset we cure.
• Score: 4.555471356313677
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. We propose an approach that extends the use of the Wasserstein Dependency Measure for learning unbiased neural text classifiers. Given the challenge of distinguishing fair from unfair information in a text encoder, we draw inspiration from adversarial training by inducing independence between representations learned for the target label and those for a sensitive attribute. We further show that Domain Adaptation can be efficiently leveraged to remove the need for access to the sensitive attributes in the dataset we cure. We provide both theoretical and empirical evidence that our approach is well-founded.

Related papers

• Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information [19.50321703079894]
  We present a novel framework to uncover the weakness of the classifier via counterfactual examples. We test the performance of our prober's misclassification detection and verify its effectiveness on the image classification benchmark datasets.
  arXiv  Detail & Related papers  (2025-03-12T05:05:58Z)
• Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning [49.417414031031264]
  This paper studies learning fair encoders in a self-supervised learning setting. All data are unlabeled and only a small portion of them are annotated with sensitive attributes.
  arXiv  Detail & Related papers  (2024-06-09T08:11:12Z)
• From Discrete to Continuous: Deep Fair Clustering With Transferable Representations [6.366934969620947]
  We propose a flexible deep fair clustering method that can handle discrete and continuous sensitive attributes simultaneously. Specifically, we design an information bottleneck style objective function to learn fair and clustering-friendly representations. Unlike existing works, we impose fairness at the representation level, which could guarantee fairness for the transferred task.
  arXiv  Detail & Related papers  (2024-03-24T15:48:29Z)
• LLM-Assisted Content Conditional Debiasing for Fair Text Embedding [37.92120550031469]
  This paper proposes a novel method for learning fair text embeddings. We define a novel content-conditional equal distance (CCED) fairness for text embeddings. We also introduce a content-conditional debiasing (CCD) loss to ensure that embeddings of texts with different sensitive attributes but identical content maintain the same distance from the embedding of their corresponding neutral text.
  arXiv  Detail & Related papers  (2024-02-22T01:20:51Z)
• Fair Text Classification with Wasserstein Independence [4.887319013701134]
  Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups remains an open challenge. This paper presents a novel method for mitigating biases in neural text classification, agnostic to the model architecture.
  arXiv  Detail & Related papers  (2023-11-21T15:51:06Z)
• Conditional Supervised Contrastive Learning for Fair Text Classification [59.813422435604025]
  We study learning fair representations that satisfy a notion of fairness known as equalized odds for text classification via contrastive learning. Specifically, we first theoretically analyze the connections between learning representations with a fairness constraint and conditional supervised contrastive objectives.
  arXiv  Detail & Related papers  (2022-05-23T17:38:30Z)
• Adversarial Stacked Auto-Encoders for Fair Representation Learning [1.061960673667643]
  We propose a new fair representation learning approach that leverages different levels of representation of data to tighten the fairness bounds of the learned representation. Our results show that stacking different auto-encoders and enforcing fairness at different latent spaces result in an improvement of fairness compared to other existing approaches.
  arXiv  Detail & Related papers  (2021-07-27T13:49:18Z)
• MultiFair: Multi-Group Fairness in Machine Learning [52.24956510371455]
  We study multi-group fairness in machine learning (MultiFair) We propose a generic end-to-end algorithmic framework to solve it. Our proposed framework is generalizable to many different settings.
  arXiv  Detail & Related papers  (2021-05-24T02:30:22Z)
• Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding [71.2260967797055]
  We propose a weakly-supervised approach for aspect-based sentiment analysis. We learn sentiment, aspect> joint topic embeddings in the word embedding space. We then use neural models to generalize the word-level discriminative information.
  arXiv  Detail & Related papers  (2020-10-13T21:33:24Z)
• Fairness by Learning Orthogonal Disentangled Representations [50.82638766862974]
  We propose a novel disentanglement approach to invariant representation problem. We enforce the meaningful representation to be agnostic to sensitive information by entropy. The proposed approach is evaluated on five publicly available datasets.
  arXiv  Detail & Related papers  (2020-03-12T11:09:15Z)
• Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning [51.742040588834996]
  Domain-adapted sentiment classification refers to training on a labeled source domain to well infer document-level sentiment on an unlabeled target domain. We propose a novel deep adversarial mutual learning approach involving two groups of feature extractors, domain discriminators, sentiment classifiers, and label probers.
  arXiv  Detail & Related papers  (2020-02-01T01:22:44Z)

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.