Diverse Adversaries for Mitigating Bias in Training
- URL: http://arxiv.org/abs/2101.10001v1
- Date: Mon, 25 Jan 2021 10:35:13 GMT
- Title: Diverse Adversaries for Mitigating Bias in Training
- Authors: Xudong Han, Timothy Baldwin, Trevor Cohn
- Abstract summary: We propose a novel approach to adversarial learning based on the use of multiple diverse discriminators.
Experimental results show that our method substantially improves over standard adversarial removal methods.
- Score: 58.201275105195485
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Adversarial learning can learn fairer and less biased models of language than
standard methods. However, current adversarial techniques only partially
mitigate model bias, added to which their training procedures are often
unstable. In this paper, we propose a novel approach to adversarial learning
based on the use of multiple diverse discriminators, whereby discriminators are
encouraged to learn orthogonal hidden representations from one another.
Experimental results show that our method substantially improves over standard
adversarial removal methods, in terms of reducing bias and the stability of
training.
Related papers
- Learning Confidence Bounds for Classification with Imbalanced Data [42.690254618937196]
We propose a novel framework that leverages learning theory and concentration inequalities to overcome the shortcomings of traditional solutions.
Our method can effectively adapt to the varying degrees of imbalance across different classes, resulting in more robust and reliable classification outcomes.
arXiv Detail & Related papers (2024-07-16T16:02:27Z) - Adversarial Reweighting Guided by Wasserstein Distance for Bias
Mitigation [24.160692009892088]
Under-representation of minorities in the data makes the disparate treatment of subpopulations difficult to deal with during learning.
We propose a novel adversarial reweighting method to address such emphrepresentation bias.
arXiv Detail & Related papers (2023-11-21T15:46:11Z) - Optimising Equal Opportunity Fairness in Model Training [60.0947291284978]
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.
arXiv Detail & Related papers (2022-05-05T01:57:58Z) - 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) - Spatial Contrastive Learning for Few-Shot Classification [9.66840768820136]
We propose a novel attention-based spatial contrastive objective to learn locally discriminative and class-agnostic features.
With extensive experiments, we show that the proposed method outperforms state-of-the-art approaches.
arXiv Detail & Related papers (2020-12-26T23:39:41Z) - One-vs.-One Mitigation of Intersectional Bias: A General Method to
Extend Fairness-Aware Binary Classification [0.48733623015338234]
One-vs.-One Mitigation is a process of comparison between each pair of subgroups related to sensitive attributes to the fairness-aware machine learning for binary classification.
Our method mitigates the intersectional bias much better than conventional methods in all the settings.
arXiv Detail & Related papers (2020-10-26T11:35:39Z) - Learning the Truth From Only One Side of the Story [58.65439277460011]
We focus on generalized linear models and show that without adjusting for this sampling bias, the model may converge suboptimally or even fail to converge to the optimal solution.
We propose an adaptive approach that comes with theoretical guarantees and show that it outperforms several existing methods empirically.
arXiv Detail & Related papers (2020-06-08T18:20:28Z)
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.