In complex networks, key nodes are important factors that directly affect network structure and functions. Therefore, accurate mining and identification of key nodes are crucial to achieving better control and a higher utilization rate of complex networks. To address this problem, this paper proposes an accurate and efficient algorithm for critical node mining. The influential nodes are determined using both global and local information (GLI) to solve the shortcoming of the existing key node identification methods that consider either local or global information. The proposed method considers two main factors, global and local influences. The global influence is determined using the K-shell hierarchical information of a node, and local influence is obtained considering the number of edges connected by the node and the given values of adjacent nodes. The given values of adjacent nodes are determined based on the degree and K-shell hierarchical information. Further, the similarity coefficient of neighbors is considered, which enhances the differentiation degree of the adjacent given values. The proposed method solves the problems of the high complexity of global information-based algorithms and the low accuracy of local information-based algorithms. The proposed method is verified by simulation experiments using the SIR and SI models as a reference, and twelve typical real-world networks are used for the comparison. The proposed GLI algorithm is compared with several common algorithms at different periods. The comparison results show that the GLI algorithm can effectively explore influential nodes in complex networks.

We study here a fixed mini-batch gradient decent (FMGD) algorithm to solve optimization problems with massive datasets. In FMGD, the whole sample is split into multiple non-overlapping partitions. Once the partitions are formed, they are then fixed throughout the rest of the algorithm. For convenience, we refer to the fixed partitions as fixed mini-batches. Then for each computation iteration, the gradients are sequentially calculated on each fixed mini-batch. Because the size of fixed mini-batches is typically much smaller than the whole sample size, it can be easily computed. This leads to much reduced computation cost for each computational iteration. It makes FMGD computationally efficient and practically more feasible. To demonstrate the theoretical properties of FMGD, we start with a linear regression model with a constant learning rate. We study its numerical convergence and statistical efficiency properties. We find that sufficiently small learning rates are necessarily required for both numerical convergence and statistical efficiency. Nevertheless, an extremely small learning rate might lead to painfully slow numerical convergence. To solve the problem, a diminishing learning rate scheduling strategy (Gitman et al., 2019) can be used. This leads to the FMGD estimator with faster numerical convergence and better statistical efficiency. Finally, the FMGD algorithms with random shuffling and a general loss function are also studied.

Background: Clinical practice guidelines (CPGs) are designed to assist doctors in clinical decision making. High-quality research articles are important for the development of good CPGs. Commonly used manual screening processes are time-consuming and labor-intensive. Artificial intelligence (AI)-based techniques have been widely used to analyze unstructured data, including texts and images. Currently, there are no effective/efficient AI-based systems for screening literature. Therefore, developing an effective method for automatic literature screening can provide significant advantages. Methods: Using advanced AI techniques, we propose the Paper title, Abstract, and Journal (PAJO) model, which treats article screening as a classification problem. For training, articles appearing in the current CPGs are treated as positive samples. The others are treated as negative samples. Then, the features of the texts (e.g., titles and abstracts) and journal characteristics are fully utilized by the PAJO model using the pretrained bidirectional-encoder-representations-from-transformers (BERT) model. The resulting text and journal encoders, along with the attention mechanism, are integrated in the PAJO model to complete the task. Results: We collected 89,940 articles from PubMed to construct a dataset related to neck pain. Extensive experiments show that the PAJO model surpasses the state-of-the-art baseline by 1.91% (F1 score) and 2.25% (area under the receiver operating characteristic curve). Its prediction performance was also evaluated with respect to subject-matter experts, proving that PAJO can successfully screen high-quality articles. Conclusions: The PAJO model provides an effective solution for automatic literature screening. It can screen high-quality articles on neck pain and significantly improve the efficiency of CPG development. The methodology of PAJO can also be easily extended to other diseases for literature screening.