相关论文: DAMEL: Dual-Axis Multi-Expert Learning for Class-I…

Multilabel classification is an emergent data mining task with a broad range of real world applications. Learning from imbalanced multilabel data is being deeply studied latterly, and several resampling methods have been proposed in the…

To address the modality learning degeneration caused by modality imbalance, existing multimodal learning~(MML) approaches primarily attempt to balance the optimization process of each modality from the perspective of model learning.…

Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

In recent years, the Deep Learning Alternating Minimization (DLAM), which is actually the alternating minimization applied to the penalty form of the deep neutral networks training, has been developed as an alternative algorithm to overcome…

Distributed ensemble learning (DEL) involves training multiple models at distributed learners, and then combining their predictions to improve performance. Existing related studies focus on DEL algorithm design and optimization but ignore…

Real-world data often follow a long-tailed distribution with a high imbalance in the number of samples between classes. The problem with training from imbalanced data is that some background features, common to all classes, can be…

Real-world datasets commonly exhibit noisy labels and class imbalance, such as long-tailed distributions. While previous research addresses this issue by differentiating noisy and clean samples, reliance on information from predictions…

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…

Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty…

We propose a new batch mode active learning algorithm designed for neural networks and large query batch sizes. The method, Discriminative Active Learning (DAL), poses active learning as a binary classification task, attempting to choose…

Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together…

We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions. Unlike conventional long-tail classifiers which operate on converged - and possibly…

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…

Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority classes. While recent methods for long-tailed recognition have mitigated this issue, they…

This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervised contrastive active learning by leveraging the contrastive…

Network traffic data is huge, varying and imbalanced because various classes are not equally distributed. Machine learning (ML) algorithms for traffic analysis uses the samples from this data to recommend the actions to be taken by the…

Relational learning aims to make relation inference by exploiting the correlations among different types of entities. Exploring relational learning on multiple bipartite graphs has been receiving attention because of its popular…

Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidence in its inference. Our goal is to design mechanisms for…

Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance and highly heterogeneous clients. We conduct a systematic…