• Corpus ID: 235623731

Fairness via Representation Neutralization

  title={Fairness via Representation Neutralization},
  author={Mengnan Du and Subhabrata Mukherjee and Guanchu Wang and Ruixiang Tang and Ahmed Hassan Awadallah and Xia Hu},
  • Mengnan Du, Subhabrata Mukherjee, +3 authors Xia Hu
  • Published 23 June 2021
  • Computer Science, Mathematics
  • ArXiv
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… 

Figures and Tables from this paper


Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
A theoretically grounded set of noise-robust loss functions that can be seen as a generalization of MAE and CCE are presented and can be readily applied with any existing DNN architecture and algorithm, while yielding good performance in a wide range of noisy label scenarios.
Penalizing unfairness in binary classification. Fairness, Accountability and Transparency in Machine Learning (FAT/ML), 2017
  • 2017
A Survey on Bias and Fairness in Machine Learning
This survey investigated different real-world applications that have shown biases in various ways, and created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems.
Explainable Deep Classification Models for Domain Generalization
This work develops a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible accuracy degradation.
Fair Mixup: Fairness via Interpolation
Fair mixup is proposed, a new data augmentation strategy for imposing the fairness constraint and it is shown that fairness can be achieved by regularizing the models on paths of interpolated samples between the groups.
FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders
This paper proposes the first neural debiasing method for a pretrained sentence encoder, which transforms the pretrained encoder outputs into debiased representations via a fair filter (FairFil) network.
Fairness in Deep Learning: A Computational Perspective
It is shown that interpretability can serve as a useful ingredient to diagnose the reasons that lead to algorithmic discrimination in deep learning, and is discussed according to three stages of deep learning life-cycle.
Decoupling Representation and Classifier for Long-Tailed Recognition
It is shown that it is possible to outperform carefully designed losses, sampling strategies, even complex modules with memory, by using a straightforward approach that decouples representation and classification.
Deep Fair Clustering for Visual Learning
This paper proposes Deep Fair Clustering (DFC) to learn fair and clustering-favorable representations for clustering simultaneously, and shows that the fairness constraint in DFC will not incur much loss in terms of several clustering metrics.
Don’t Judge an Object by Its Context: Learning to Overcome Contextual Bias
This work focuses on addressing contextual biases to improve the robustness of the learnt feature representations of a category from its co-occurring context by learning a feature subspace that explicitly represents categories occurring in the absence of context along side a joint feature sub space that represents both categories and context.