Related papers: Multi-Granularity Regularized Re-Balancing for Cla…
Large language models (LLMs) have shown impressive performance on downstream tasks through in-context learning (ICL), which heavily relies on the demonstrations selected from annotated datasets. However, these datasets often exhibit…
Existing multi-label frameworks only exploit the information deduced from the bipartition of the labels into a positive and negative set. Therefore, they do not benefit from the ranking order between positive labels, which is the concept we…
Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. This problem usually arises due to the overfitting problem, which is characterized by learning everything presented in the…
Improving the classification of multi-class imbalanced data is more difficult than its two-class counterpart. In this paper, we use deep neural networks to train new representations of tabular multi-class data. Unlike the typically…
Imbalanced node classification is a critical challenge in graph learning, where most existing methods typically utilize Graph Neural Networks (GNNs) to learn node representations. These methods can be broadly categorized into the data-level…
The Lifelong Multi-Label (LML) image recognition builds an online class-incremental classifier in a sequential multi-label image recognition data stream. The key challenges of LML image recognition are the construction of label…
Class imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. One efficient and flexible strategy to deal with this problem is to employ sampling techniques before training a multi-label…
Class imbalance remains a significant challenge in machine learning, particularly for tabular data classification tasks. While Gradient Boosting Decision Trees (GBDT) models have proven highly effective for such tasks, their performance can…
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…
Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often…
Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…
A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However,…
Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption always fails to…
This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current…
Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases,…
Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a…
Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To…
Learning new tasks accumulatively without forgetting remains a critical challenge in continual learning. Generative experience replay addresses this challenge by synthesizing pseudo-data points for past learned tasks and later replaying…
Multi-view learning is widely applied to real-life datasets, such as multiple omics biological data, but it often suffers from both missing views and missing labels. Prior probabilistic approaches addressed the missing view problem by using…
Class imbalance poses a major challenge in different classification tasks, which is a frequently occurring scenario in many real-world applications. Data resampling is considered to be the standard approach to address this issue. The goal…