Graph-Based Class-Imbalance Learning With Label Enhancement

Distance-Aware Learning for Inductive Link Prediction on Temporal Networks

Inductive link prediction on temporal networks aims to predict the future links associated with node(s) unseen in the historical timestamps. Existing methods generate the predictions mainly by learning node representation from the node/edge attributes as well as the network dynamics or by measuring the distance between nodes on the temporal network structure. However, the attribute information is unavailable in many realistic applications and the structure-aware methods highly rely on nodes' common neighbors, which are difficult to accurately detect, especially in sparse temporal networks. Thus, we propose a distance-aware learning (DEAL) approach for inductive link prediction on temporal networks. Specifically, we first design an adaptive sampling method to extract temporal adaptive walks for nodes, increasing the probability of including the common neighbors between nodes. Then, we design a dual-channel distance measuring component, which simultaneously measures the distance between nodes in the embedding space and on the dynamic graph structure for predicting future inductive edges. Extensive experiments are conducted on three public temporal network datasets, i.e., MathOverflow, AskUbuntu, and StackOverflow. The experimental results validate the superiority of DEAL over the state-of-the-art baselines in terms of accuracy, area under the ROC curve (AUC), and average precision (AP), where the improvements are especially obvious in scenarios with only limited data.

Knowledge Fusion Distillation: Improving Distillation with Multi-scale Attention Mechanisms

The success of deep learning has brought breakthroughs in many fields. However, the increased performance of deep learning models is often accompanied by an increase in their depth and width, which conflicts with the storage, energy consumption, and computational power of edge devices. Knowledge distillation, as an effective model compression method, can transfer knowledge from complex teacher models to student models. Self-distillation is a special type of knowledge distillation, which does not to require a pre-trained teacher model. However, existing self-distillation methods rarely consider how to effectively use the early features of the model. Furthermore, most self-distillation methods use features from the deepest layers of the network to guide the training of the branches of the network, which we find is not the optimal choice. In this paper, we found that the feature maps obtained by early feature fusion do not serve as a good teacher to guide their own training. Based on this, we propose a selective feature fusion module and further obtain a new self-distillation method, knowledge fusion distillation. Extensive experiments on three datasets have demonstrated that our method has comparable performance to state-of-the-art distillation methods. In addition, the performance of the network can be further enhanced when fused features are integrated into the network.

Mortality Prediction of COVID-19 Patients Using Radiomic and Neural Network Features Extracted from a Wide Chest X-ray Sample Size: A Robust Approach for Different Medical Imbalanced Scenarios

Aim: The aim of this study was to develop robust prognostic models for mortality prediction of COVID-19 patients, applicable to different sets of real scenarios, using radiomic and neural network features extracted from chest X-rays (CXRs) with a certified and commercially available software. Methods: 1816 patients from 5 different hospitals in the Province of Reggio Emilia were included in the study. Overall, 201 radiomic features and 16 neural network features were extracted from each COVID-19 patient’s radiography. The initial dataset was balanced to train the classifiers with the same number of dead and survived patients, randomly selected. The pipeline had three main parts: balancing procedure; three-step feature selection; and mortality prediction with radiomic features through three machine learning (ML) classification models: AdaBoost (ADA), Quadratic Discriminant Analysis (QDA) and Random Forest (RF). Five evaluation metrics were computed on the test samples. The performance for death prediction was validated on both a balanced dataset (Case 1) and an imbalanced dataset (Case 2). Results: accuracy (ACC), area under the ROC-curve (AUC) and sensitivity (SENS) for the best classifier were, respectively, 0.72 ± 0.01, 0.82 ± 0.02 and 0.84 ± 0.04 for Case 1 and 0.70 ± 0.04, 0.79 ± 0.03 and 0.76 ± 0.06 for Case 2. These results show that the prediction of COVID-19 mortality is robust in a different set of scenarios. Conclusions: Our large and varied dataset made it possible to train ML algorithms to predict COVID-19 mortality using radiomic and neural network features of CXRs.