Fairness via Representation Neutralization

• URL: http://arxiv.org/abs/2106.12674v1
• Date: Wed, 23 Jun 2021 22:26:29 GMT
• Title: Fairness via Representation Neutralization
• Authors: Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Hu
• Abstract summary: We propose a new mitigation technique, namely, Representation Neutralization for Fairness (RNF) RNF achieves that fairness by debiasing only the task-specific classification head of DNN models. Experimental results over several benchmark datasets demonstrate our RNF framework to effectively reduce discrimination of DNN models.
• Score: 60.90373932844308
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing bias mitigation methods for DNN models primarily work on learning debiased encoders. This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information has been removed from the encoder. To address these limitations, we explore the following research question: Can we reduce the discrimination of DNN models by only debiasing the classification head, even with biased representations as inputs? To this end, we propose a new mitigation technique, namely, Representation Neutralization for Fairness (RNF) that achieves fairness by debiasing only the task-specific classification head of DNN models. To this end, we leverage samples with the same ground-truth label but different sensitive attributes, and use their neutralized representations to train the classification head of the DNN model. The key idea of RNF is to discourage the classification head from capturing spurious correlation between fairness sensitive information in encoder representations with specific class labels. To address low-resource settings with no access to sensitive attribute annotations, we leverage a bias-amplified model to generate proxy annotations for sensitive attributes. Experimental results over several benchmark datasets demonstrate our RNF framework to effectively reduce discrimination of DNN models with minimal degradation in task-specific performance.

Related papers

• MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage [1.8238848494579714]
  We propose a novel model-agnostic debiasing framework named MAPPING for fair node classification. Our results show that MAPPING can achieve better trade-offs between utility and fairness, and privacy risks of sensitive information leakage.
  arXiv  Detail & Related papers  (2024-01-23T14:59:46Z)
• Marginal Debiased Network for Fair Visual Recognition [59.05212866862219]
  We propose a novel marginal debiased network (MDN) to learn debiased representations. Our MDN can achieve a remarkable performance on under-represented samples.
  arXiv  Detail & Related papers  (2024-01-04T08:57:09Z)
• TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes [4.2560452339165895]
  Targeted Concept Erasure (TaCo) is a novel approach that removes sensitive information from final latent representations. Our experiments show that TaCo outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-11T16:22:37Z)
• Self-supervised debiasing using low rank regularization [59.84695042540525]
  Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. We propose a self-supervised debiasing framework potentially compatible with unlabeled samples. Remarkably, the proposed debiasing framework significantly improves the generalization performance of self-supervised learning baselines.
  arXiv  Detail & Related papers  (2022-10-11T08:26:19Z)
• Mitigating Algorithmic Bias with Limited Annotations [65.060639928772]
  When sensitive attributes are not disclosed or available, it is needed to manually annotate a small part of the training data to mitigate bias. We propose Active Penalization Of Discrimination (APOD), an interactive framework to guide the limited annotations towards maximally eliminating the effect of algorithmic bias. APOD shows comparable performance to fully annotated bias mitigation, which demonstrates that APOD could benefit real-world applications when sensitive information is limited.
  arXiv  Detail & Related papers  (2022-07-20T16:31:19Z)
• Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation [55.27563366506407]
  We introduce a discriminator-free adversarial learning network (DALN) for unsupervised domain adaptation (UDA) DALN achieves explicit domain alignment and category distinguishment through a unified objective. DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets.
  arXiv  Detail & Related papers  (2022-04-08T04:40:18Z)
• Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder [92.67156911466397]
  We propose a semi-supervised fair representation learning approach based on adversarial variational autoencoder. We use a bias-aware model to capture inherent bias information on sensitive attribute. We also use a bias-free model to learn debiased fair representations by using adversarial learning to remove bias information from them.
  arXiv  Detail & Related papers  (2022-04-01T15:57:47Z)
• EqGNN: Equalized Node Opportunity in Graphs [19.64827998759028]
  Graph neural networks (GNNs) have been widely used for supervised learning tasks in graphs. Some ignore the sensitive attributes or optimize for the criteria of statistical parity for fairness. We present a GNN framework that allows optimizing representations for the notion of Equalized Odds fairness criteria.
  arXiv  Detail & Related papers  (2021-08-19T17:17:24Z)

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.