Related papers: Class-attribute Priors: Adapting Optimization to H…

In real-world applications, as data availability increases, obtaining labeled data for machine learning (ML) projects remains challenging due to the high costs and intensive efforts required for data annotation. Many ML projects,…

We investigate the problem of classification in the presence of unknown class-conditional label noise in which the labels observed by the learner have been corrupted with some unknown class dependent probability. In order to obtain finite…

Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization,…

With the advent of big data across multiple high-impact applications, we are often facing the challenge of complex heterogeneity. The newly collected data usually consist of multiple modalities and are characterized with multiple labels,…

In cases of uncertainty, a multi-class classifier preferably returns a set of candidate classes instead of predicting a single class label with little guarantee. More precisely, the classifier should strive for an optimal balance between…

Unlike the typical classification setting where each instance is associated with a single class, in multi-label learning each instance is associated with multiple classes simultaneously. Therefore the learning task in this setting is to…

This paper explores the complex tradeoffs between various fairness metrics such as equalized odds, disparate impact, and equal opportunity and predictive accuracy within COMPAS by building neural networks trained with custom loss functions…

Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e., instances of the same class share the…

Real-world object classes appear in imbalanced ratios. This poses a significant challenge for classifiers which get biased towards frequent classes. We hypothesize that improving the generalization capability of a classifier should improve…

Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively…

We explore contemporary robust classification algorithms for overcoming class-dependant labelling noise: Forward, Importance Re-weighting and T-revision. The classifiers are trained and evaluated on class-conditional random label noise data…

Motivated by applications in protein function prediction, we consider a challenging supervised classification setting in which positive labels are scarce and there are no explicit negative labels. The learning algorithm must thus select…

In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial…

The fairness in machine learning is getting increasing attention, as its applications in different fields continue to expand and diversify. To mitigate the discriminated model behaviors between different demographic groups, we introduce a…

Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require…

Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail…

We present Self-Classifier -- a novel self-supervised end-to-end classification learning approach. Self-Classifier learns labels and representations simultaneously in a single-stage end-to-end manner by optimizing for same-class prediction…

Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two…

This paper strives to address image classifier bias, with a focus on both feature and label embedding spaces. Previous works have shown that spurious correlations from protected attributes, such as age, gender, or skin tone, can cause…

We present consistent algorithms for multiclass learning with complex performance metrics and constraints, where the objective and constraints are defined by arbitrary functions of the confusion matrix. This setting includes many common…