相关论文: ReMix: Calibrated Resampling for Class Imbalance i…

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…

We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs. First, we show that a deep CNN with an architecture inspired by the models recently…

Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue. The most competitive noisy-label learning algorithms rely on a 2-stage…

Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…

The detection of cyber-attacks in computer networks is a crucial and ongoing research challenge. Machine learning-based attack classification offers a promising solution, as these models can be continuously updated with new data, enhancing…

Class-imbalanced learning (CIL) on tabular data is important in many real-world applications where the minority class holds the critical but rare outcomes. In this paper, we present CLIMB, a comprehensive benchmark for class-imbalanced…

Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skewness of the distribution of classes; therefore, tend to be…

Handling imbalance in class distribution when building a classifier over tabular data has been a problem of long-standing interest. One popular approach is augmenting the training dataset with synthetically generated data. While classical…

A machine learning model is calibrated if its predicted probability for an outcome matches the observed frequency for that outcome conditional on the model prediction. This property has become increasingly important as the impact of machine…

Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active…

Boosting is a learning scheme that combines weak prediction rules to produce a strong composite estimator, with the underlying intuition that one can obtain accurate prediction rules by combining "rough" ones. Although boosting is proved to…

Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance…

Class imbalance severely impacts machine learning performance on minority classes in real-world applications. While various solutions exist, active learning offers a fundamental fix by strategically collecting balanced, informative labeled…

Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models. Most existing studies are rooted in a class-rebalancing (CR) perspective and address class imbalance with class-wise…

Imbalanced data occurs in a wide range of scenarios. The skewed distribution of the target variable elicits bias in machine learning algorithms. One of the popular methods to combat imbalanced data is to artificially balance the data…

Deep neural networks (DNNs) have demonstrated promising results in various complex tasks. However, current DNNs encounter challenges with over-parameterization, especially when there is limited training data available. To enhance the…

Federated Learning (FL) enables collaborative model training across decentralized devices while preserving data privacy. However, real-world FL deployments face critical challenges such as data imbalances, including label noise and non-IID…

Crash data is often greatly imbalanced, with the majority of crashes being non-fatal crashes, and only a small number being fatal crashes due to their rarity. Such data imbalance issue poses a challenge for crash severity modeling since it…

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where…

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…