Related papers: Balanced Datasets Are Not Enough: Estimating and M…

Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition. But do unsupervised computer vision…

Ensembling is commonly regarded as an effective way to improve the general performance of models in machine learning, while also increasing the robustness of predictions. When it comes to algorithmic fairness, heterogeneous ensembles,…

Recent work has shown that deep vision models tend to be overly dependent on low-level or "texture" features, leading to poor generalization. Various data augmentation strategies have been proposed to overcome this so-called texture bias in…

We tackle the problem of bias mitigation of algorithmic decisions in a setting where both the output of the algorithm and the sensitive variable are continuous. Most of prior work deals with discrete sensitive variables, meaning that the…

Machine learning models trained on imbalanced datasets often exhibit intersectional biases-systematic errors arising from the interaction of multiple attributes such as object class and environmental conditions. This paper presents a…

Visual sentiment analysis has received increasing attention in recent years. However, the dataset's quality is a concern because the sentiment labels are crowd-sourcing, subjective, and prone to mistakes, and poses a severe threat to the…

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation…

An increased awareness concerning risks of algorithmic bias has driven a surge of efforts around bias mitigation strategies. A vast majority of the proposed approaches fall under one of two categories: (1) imposing algorithmic fairness…

Pedestrian attribute recognition is an important multi-label classification problem. Although the convolutional neural networks are prominent in learning discriminative features from images, the data imbalance in multi-label setting for…

Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification, we consider the setting where we have an error distribution…

Face recognition and verification are two computer vision tasks whose performance has progressed with the introduction of deep representations. However, ethical, legal, and technical challenges due to the sensitive character of face data…

NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples…

Deep neural networks trained on biased data often inadvertently learn unintended inference rules, particularly when labels are strongly correlated with biased features. Existing bias mitigation methods typically involve either a)…

The adoption of diagnosis and prognostic algorithms in healthcare has led to concerns about the perpetuation of bias against disadvantaged groups of individuals. Deep learning methods to detect and mitigate bias have revolved around…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

Stance detection models may tend to rely on dataset bias in the text part as a shortcut and thus fail to sufficiently learn the interaction between the targets and texts. Recent debiasing methods usually treated features learned by small…

A key obstacle in automated analytics and meta-learning is the inability to recognize when different datasets contain measurements of the same variable. Because provided attribute labels are often uninformative in practice, this task may be…

Automated Machine Learning has grown very successful in automating the time-consuming, iterative tasks of machine learning model development. However, current methods struggle when the data is imbalanced. Since many real-world datasets are…

Robots should be able to learn complex behaviors from human demonstrations. In practice, these human-provided datasets are inevitably imbalanced: i.e., the human demonstrates some subtasks more frequently than others. State-of-the-art…

Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. Although previous approaches pre-define the type of dataset bias to prevent the…