Optimising Equal Opportunity Fairness in Model Training
- URL: http://arxiv.org/abs/2205.02393v1
- Date: Thu, 5 May 2022 01:57:58 GMT
- Title: Optimising Equal Opportunity Fairness in Model Training
- Authors: Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin, Lea Frermann
- Abstract summary: Existing debiasing methods, such as adversarial training and removing protected information from representations, have been shown to reduce bias.
We propose two novel training objectives which directly optimise for the widely-used criterion of it equal opportunity, and show that they are effective in reducing bias while maintaining high performance over two classification tasks.
- Score: 60.0947291284978
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Real-world datasets often encode stereotypes and societal biases. Such biases
can be implicitly captured by trained models, leading to biased predictions and
exacerbating existing societal preconceptions. Existing debiasing methods, such
as adversarial training and removing protected information from
representations, have been shown to reduce bias. However, a disconnect between
fairness criteria and training objectives makes it difficult to reason
theoretically about the effectiveness of different techniques. In this work, we
propose two novel training objectives which directly optimise for the
widely-used criterion of {\it equal opportunity}, and show that they are
effective in reducing bias while maintaining high performance over two
classification tasks.
Related papers
- Improving Bias Mitigation through Bias Experts in Natural Language
Understanding [10.363406065066538]
We propose a new debiasing framework that introduces binary classifiers between the auxiliary model and the main model.
Our proposed strategy improves the bias identification ability of the auxiliary model.
arXiv Detail & Related papers (2023-12-06T16:15:00Z) - Language Models Get a Gender Makeover: Mitigating Gender Bias with
Few-Shot Data Interventions [50.67412723291881]
Societal biases present in pre-trained large language models are a critical issue.
We propose data intervention strategies as a powerful yet simple technique to reduce gender bias in pre-trained models.
arXiv Detail & Related papers (2023-06-07T16:50:03Z) - 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) - A Differentiable Distance Approximation for Fairer Image Classification [31.471917430653626]
We propose a differentiable approximation of the variance of demographics, a metric that can be used to measure the bias, or unfairness, in an AI model.
Our approximation can be optimised alongside the regular training objective which eliminates the need for any extra models during training.
We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios.
arXiv Detail & Related papers (2022-10-09T23:02:18Z) - Towards Equal Opportunity Fairness through Adversarial Learning [64.45845091719002]
Adversarial training is a common approach for bias mitigation in natural language processing.
We propose an augmented discriminator for adversarial training, which takes the target class as input to create richer features.
arXiv Detail & Related papers (2022-03-12T02:22:58Z) - Contrastive Learning for Fair Representations [50.95604482330149]
Trained classification models can unintentionally lead to biased representations and predictions.
Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise.
We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
arXiv Detail & Related papers (2021-09-22T10:47:51Z) - Fairness-aware Class Imbalanced Learning [57.45784950421179]
We evaluate long-tail learning methods for tweet sentiment and occupation classification.
We extend a margin-loss based approach with methods to enforce fairness.
arXiv Detail & Related papers (2021-09-21T22:16:30Z) - Towards Accuracy-Fairness Paradox: Adversarial Example-based Data
Augmentation for Visual Debiasing [15.689539491203373]
Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks.
This paper studies the debiasing problem in the context of image classification tasks.
arXiv Detail & Related papers (2020-07-27T15:17:52Z)
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.