相关论文: Fair Attribute Classification through Latent Space…

Machine learning models have demonstrated promising performance in many areas. However, the concerns that they can be biased against specific demographic groups hinder their adoption in high-stake applications. Thus, it is essential to…

Face gender classification models often reflect and amplify demographic biases present in their training data, leading to uneven performance across gender and racial subgroups. We introduce pseudo-balancing, a simple and effective strategy…

Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

Generative Adversarial Networks (GAN) is currently widely used as an unsupervised image generation method. Current state-of-the-art GANs can generate photorealistic images with high resolution. However, a large amount of data is required,…

Galaxy morphologies and their relation with physical properties have been a relevant subject of study in the past. Most galaxy morphology catalogs have been labelled by human annotators or by machine learning models trained on human…

In this paper, we introduce FairFaceGAN, a fairness-aware facial Image-to-Image translation model, mitigating the problem of unwanted translation in protected attributes (e.g., gender, age, race) during facial attributes editing. Unlike…

Generative adversarial networks (GANs)successfully generate high quality data by learning amapping from a latent vector to the data. Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for…

Naively trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solutions to this problem come at the…

The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We address this problem by introducing fairness-aware…

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution and drug discovery, etc., by now, the inner process of GANs is far from been understood. To get deeper…

We present a novel self-supervised learning approach for conditional generative adversarial networks (GANs) under a semi-supervised setting. Unlike prior self-supervised approaches which often involve geometric augmentations on the image…

Data sets for fairness relevant tasks can lack examples or be biased according to a specific label in a sensitive attribute. We demonstrate the usefulness of weight based meta-learning approaches in such situations. For models that can be…

In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Recent research addresses…

In this paper, we consider a theoretical model for injecting data bias, namely, under-representation and label bias (Blum & Stangl, 2019). We empirically study the effect of varying data biases on the accuracy and fairness of fair…

Recent works in artificial intelligence fairness attempt to mitigate discrimination by proposing constrained optimization programs that achieve parity for some fairness statistic. Most assume availability of the class label, which is…

Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs). However, existing approaches are mostly designed in an unsupervised manner while little attention has been paid to domain…

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…

A key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time. As such, these methods often perform poorly in the face of biased data,…

Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval. In this work, we consider the potential bias based on…

Modern machine learning (ML) models are becoming increasingly popular and are widely used in decision-making systems. However, studies have shown critical issues of ML discrimination and unfairness, which hinder their adoption on high-stake…