Search Results

Graph neural networks (GNNs) have gained traction and have been applied to various graph-based data analysis tasks due to their high performance. However, a major concern is their robustness, particularly when faced with graph data that has been ...

Unsupervised Domain Adaptation (UDA) intends to achieve excellent results by transferring knowledge from labeled source domains to unlabeled target domains in which the data or label distribution changes. Previous UDA methods have acquired great ...

Recently, crowdsourcing has established itself as an efficient labeling solution by distributing tasks to crowd workers. As the workers can make mistakes with diverse expertise, one core learning task is to estimate each worker’s expertise, and ...

Deep learning has achieved remarkable success in graph-related tasks, yet this accomplishment heavily relies on large-scale high-quality annotated datasets. However, acquiring such datasets can be cost-prohibitive, leading to the practical use of labels ...

Conformal Prediction (CP) quantifies network uncertainty by building a small prediction set with a pre-defined probability that the correct class is within this set. In this study we tackle the problem of CP calibration based on a validation set ...

Active client selection (ACS) strategically identifies clients for model updates during each training round of federated learning. In scenarios with limited communication resources, ACS emerges as a superior alternative to random client selection,...

The success of GNNs highly relies on the accurate labeling of data. Existing methods of ensuring accurate labels, such as weakly-supervised learning, mainly focus on the existing nodes in the graphs. However, in reality, new nodes always continuously ...

Most natural language processing tasks rely on massive labeled data to train an outstanding neural network model. However, the label noise (i.e., wrong label) is inevitably introduced when annotating large-scale text datasets, which significantly ...

The use of all samples in the optimization process does not produce robust results in datasets with label noise. Because the gradients calculated according to the losses of the noisy samples cause the optimization process to go in the wrong ...

Graph Neural Networks (GNNs) have garnered considerable interest due to their exceptional performance in a wide range of graph machine learning tasks. Nevertheless, the majority of GNN-based approaches have been examined using well-annotated benchmark ...

Noisy labels hurt deep learning-based supervised image classification performance as the models may overfit the noise and learn corrupted feature extractors. For natural image classification training with noisy labeled data, model initialization ...

The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e.g., via crowdsourcing). A typical way of using these separate labels is to first aggregate them into one and apply standard training ...

The amount of data generated daily grows tremendously in virtually all domains of science and industry, and its efficient storage, processing and analysis pose significant practical challenges nowadays. To automate the process of extracting useful ...

In recent years, the imbalanced classification problem has received much attention. SMOTE is one of the most popular methods to improve the performance of unbalanced data classification models. SMOTE changes the data distribution of unbalanced data ...

Single-label facial expression recognition (FER), which aims to classify single expression for facial images, usually suffers from the label noisy and incomplete problem, where manual annotations for partial training images exist wrong or incomplete ...

Graph Neural Networks (GNNs) have become widely-used models for semi-supervised learning. However, the robustness of GNNs in the presence of label noise remains a largely under-explored problem. In this paper, we consider an important yet challenging ...

In this work, we provide a characterization of the feature-learning process in two-layer ReLU networks trained by gradient descent on the logistic loss following random initialization. We consider data with binary labels that are generated by an XOR-like ...

Positive-Unlabeled learning (PU learning) is a special case of semi-supervised binary classification where only a fraction of positive examples is labeled. The challenge is then to find the correct classifier despite this lack of information. Recently, ...

Music recommendation is usually modeled as a Click-Through Rate (CTR) prediction problem, which estimates the probability of a user listening a recommended song. CTR prediction can be formulated as a binary classification problem where the played songs ...

Robustness is becoming another important challenge of federated learning in that the data collection process in each client is naturally accompanied by noisy labels. However, it is far more complex and challenging owing to varying levels of data ...