Related papers: A Debiased Nearest Neighbors Framework for Multi-L…

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are…

Deep neural networks (DNNs) enable innovative applications of machine learning like image recognition, machine translation, or malware detection. However, deep learning is often criticized for its lack of robustness in adversarial settings…

Machine learning for text classification is the underpinning of document cataloging, news filtering, document steering and exemplification. In text mining realm, effective feature selection is significant to make the learning task more…

While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects,…

Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are crucial yet challenging for real-world applications like search…

In recent years, many deep-learning based models are proposed for text classification. This kind of models well fits the training set from the statistical point of view. However, it lacks the capacity of utilizing instance-level information…

We present Multi-Scale Label Dependence Relation Networks (MSDN), a novel approach to multi-label classification (MLC) using 1-dimensional convolution kernels to learn label dependencies at multi-scale. Modern multi-label classifiers have…

Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural…

Hierarchical multi-label text classification (HMTC) has been gaining popularity in recent years thanks to its applicability to a plethora of real-world applications. The existing HMTC algorithms largely focus on the design of classifiers,…

Graph Neural Networks (GNNs) have been widely employed for semi-supervised node classification tasks on graphs. However, the performance of GNNs is significantly affected by label noise, that is, a small amount of incorrectly labeled nodes…

Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation criterion. When solving the MLC problems, we generally expect…

Despite remarkable success in diverse web-based applications, Graph Neural Networks(GNNs) inherit and further exacerbate historical discrimination and social stereotypes, which critically hinder their deployments in high-stake domains such…

Distance-based unsupervised text classification is a method within text classification that leverages the semantic similarity between a label and a text to determine label relevance. This method provides numerous benefits, including fast…

The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient…

Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases…

Discovering fine-grained categories from coarsely labeled data is a practical and challenging task, which can bridge the gap between the demand for fine-grained analysis and the high annotation cost. Previous works mainly focus on…

Kernel Density Estimation (KDE) is a nonparametric method for estimating the shape of a density function, given a set of samples from the distribution. Recently, locality-sensitive hashing, originally proposed as a tool for nearest neighbor…

Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…

We propose Distribution Embedding Networks (DEN) for classification with small data. In the same spirit of meta-learning, DEN learns from a diverse set of training tasks with the goal to generalize to unseen target tasks. Unlike existing…

Deep convolution neural networks (CNN) have demonstrated advanced performance on single-label image classification, and various progress also have been made to apply CNN methods on multi-label image classification, which requires to…