Related papers: Introducing Curvature to the Label Space

Sentiment analysis is a key component in various text mining applications. Numerous sentiment classification techniques, including conventional and deep learning-based methods, have been proposed in the literature. In most existing methods,…

Curriculum learning can improve neural network training by guiding the optimization to desirable optima. We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label…

For the advancements of time series classification, scrutinizing previous studies, most existing methods adopt a common learning-to-classify paradigm - a time series classifier model tries to learn the relation between sequence inputs and…

Recently, an end-to-end two-dimensional sound source localization algorithm with ad-hoc microphone arrays formulates the sound source localization problem as a classification problem. The algorithm divides the target indoor space into a set…

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…

Graph-based semi-supervised learning is the problem of propagating labels from a small number of labelled data points to a larger set of unlabelled data. This paper is concerned with the consistency of optimization-based techniques for such…

Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member of a set of objects, including a background class,…

Categorical features are present in about 40% of real world problems, highlighting the crucial role of encoding as a preprocessing component. Some recent studies have reported benefits of the various target-based encoders over classical…

Representing a label distribution as a one-hot vector is a common practice in training node classification models. However, the one-hot representation may not adequately reflect the semantic characteristics of a node in different classes,…

Model calibration seeks to ensure that models produce confidence scores that accurately reflect the true likelihood of their predictions being correct. However, existing calibration approaches are fundamentally tied to datasets of one-hot…

Categorical variables often appear in datasets for classification and regression tasks, and they need to be encoded into numerical values before training. Since many encoders have been developed and can significantly impact performance,…

Multi-label learning is concerned with the classification of data with multiple class labels. This is in contrast to the traditional classification problem where every data instance has a single label. Due to the exponential size of output…

Text classification in education, usually called auto-tagging, is the automated process of assigning relevant tags to educational content, such as questions and textbooks. However, auto-tagging suffers from a data scarcity problem, which…

Hierarchical text classification (HTC) is the task of assigning labels to a text within a structured space organized as a hierarchy. Recent works treat HTC as a conventional multilabel classification problem, therefore evaluating it as…

In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner. The main idea is to…

One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at…

Class imbalance, which is also called long-tailed distribution, is a common problem in classification tasks based on machine learning. If it happens, the minority data will be overwhelmed by the majority, which presents quite a challenge…

Despite the great success of state-of-the-art deep neural networks, several studies have reported models to be over-confident in predictions, indicating miscalibration. Label Smoothing has been proposed as a solution to the over-confidence…

Statistical models usually require vector representations of categorical variables, using for instance one-hot encoding. This strategy breaks down when the number of categories grows, as it creates high-dimensional feature vectors.…

We propose a method to reduce the complexity of Generalized Linear Models in the presence of categorical predictors. The traditional one-hot encoding, where each category is represented by a dummy variable, can be wasteful, difficult to…