Search

Quantifying the impact of a scholarly paper is of great significance, yet the effect of geographical distance of cited papers has not been explored. In this paper, we examine 30,596 papers published in Physical Review C, and identify the relationship between citations and geographical distances between author affiliations. Subsequently, a relative citation weight is applied to assess the impact of a scholarly paper. A higher-order weighted quantum PageRank algorithm is also developed to address the behavior of multiple step citation flow. Capturing the citation dynamics with higher-order dependencies reveals the actual impact of papers, including necessary self-citations that are sometimes excluded in prior studies. Quantum PageRank is utilized in this paper to help differentiating nodes whose PageRank values are identical.

Anomaly analytics is a popular and vital task in various research contexts that has been studied for several decades. At the same time, deep learning has shown its capacity in solving many graph-based tasks, like node classification, link prediction, and graph classification. Recently, many studies are extending graph learning models for solving anomaly analytics problems, resulting in beneficial advances in graph-based anomaly analytics techniques. In this survey, we provide a comprehensive overview of graph learning methods for anomaly analytics tasks. We classify them into four categories based on their model architectures, namely graph convolutional network, graph attention network, graph autoencoder, and other graph learning models. The differences between these methods are also compared in a systematic manner. Furthermore, we outline several graph-based anomaly analytics applications across various domains in the real world. Finally, we discuss five potential future research directions in this rapidly growing field. [ABSTRACT FROM AUTHOR]

Evaluating the impact of a scholarly article is of great significance and has attracted great attentions. Although citation-based evaluation approaches have been widely used, these approaches face limitations e.g. in identifying anomalous citations patterns. This negligence would inevitably cause unfairness and inaccuracy to the article impact evaluation. In this study, in order to discover the anomalous citations and ensure the fairness and accuracy of research outcome evaluation, we investigate the citation relationships between articles using the following factors: collaboration times, the time span of collaboration, citing times and the time span of citing to weaken the relationship of Conflict of Interest (COI) in the citation network. Meanwhile, we study a special kind of COI, namely suspected COI relationship. Based on the COI relationship, we further bring forward the COIRank algorithm, an innovative scheme for accurately assessing the impact of an article. Our method distinguishes the citation strength, and utilizes PageRank and HITS algorithms to rank scholarly articles comprehensively. The experiments are conducted on the American Physical Society (APS) dataset. We find that about 80.88% articles contain contributed citations by co-authors in 26,366 articles and 75.55% articles among these articles are cited by the authors belonging to the same affiliation, indicating COI and suspected COI should not be ignored for evaluating impact of scientific papers objectively. Moreover, our experimental results demonstrate COIRank algorithm significantly outperforms the state-of-art solutions. The validity of our approach is verified by using the probability of Recommendation Intensity. [ABSTRACT FROM AUTHOR]

Balancing the convergence and diversity in the multi-objective firefly algorithm is essential for obtaining high precision and well distributed Pareto front. However, most existing algorithms cannot​ guarantee such balance, leading to a poor comprehensive performance. To address this limitation, this paper proposes a multi-strategy ensemble firefly algorithm with equilibrium of convergence and diversity (MEFA-CD). Firstly, an improved linear congruence method is used to generate the initial population with uniform distribution, to provide a good start for the subsequent population evolution and ensure the global search ability; Secondly, a hybrid learning strategy is utilized to identify the best elite solution according to the maximum fitness value. Combined with the current best solution, the firefly is guided to learn under the effect of compensation factor. On the one hand, it breaks through the population constraints, which yields a faster convergence to the Pareto optimal solution set. On the other hand, it expands the search range of the population, which improves the diversity and the accuracy of the Pareto optimal set; Finally, the crowding distance mechanism is used to delete the aggregation solution, which maintains the diversity of external files and ensures the local development ability of the population, and further improves the convergence of the algorithm. Experimental results show that, compared with other multi-objective optimization algorithms, the proposed algorithm has better performance in convergence and diversity, among which the optimization performance is improved by 61% compared with the standard MOFA. • A novel MOEA with equilibrium of convergence and diversity is proposed. • A strategy for generating uniformly distributed initial solutions is proposed. • A hybrid learning strategy for enhancing the convergence and diversity of the algorithm is proposed. • The collaboration between multiple strategies to balance the exploration and development of the algorithm. [ABSTRACT FROM AUTHOR]

• Propose a weighted hybrid multi-view fusion method for the semi-supervised classification problem. • Introduce Variant Alternating Splitting Augmented Lagrangian Method to solve the rank consistency problem. • Design an efficient iterative algorithm to optimize the objective function. This paper proposes a weighted hybrid multi-view fusion method for the semi-supervised classification problem. Instead of getting access to the features from different views directly, this method utilizes the square losses of the multi-view classifiers to exploit the between-view relationship, which preserves the privacy of data. Considering the different prediction capability of classifiers on multiple views, an objective function with the constraint of rank consistency is constructed to weight view-specific learners adaptively, where the constraint makes each view-specific learner improve its performance by exploring the predicted results of other learners. Furthermore, an iterative algorithm based on the Variant Alternating Splitting Augmented Lagrangian Method (VASALM) and the quadratic programming method is developed to optimize the objective function. Experimental results on different real-world datasets demonstrate the effectiveness of the proposed method for multi-view learning. The experiments also analyze parameter sensitivity and convergency of the optimization algorithm. [ABSTRACT FROM AUTHOR]

The goals of this research were to search for Convolutional Neural Network (CNN) architectures, suitable for an on-device processor with limited computing resources, performing at substantially lower Network Architecture Search (NAS) costs. A new algorithm entitled an Early Exit Population Initialisation (EE-PI) for Evolutionary Algorithm (EA) was developed to achieve both goals. The EE-PI reduces the total number of parameters in the search process by filtering the models with fewer parameters than the maximum threshold. It will look for a new model to replace those models with parameters more than the threshold. Thereby, reducing the number of parameters, memory usage for model storage and processing time while maintaining the same performance or accuracy. The search time was reduced to 0.52 GPU day. This is a huge and significant achievement compared to the NAS of 4 GPU days achieved using NSGA-Net, 3,150 GPU days by the AmoebaNet model, and the 2,000 GPU days by the NASNet model. As well, Early Exit Evolutionary Algorithm networks (EEEA-Nets) yield network architectures with minimal error and computational cost suitable for a given dataset as a class of network algorithms. Using EEEA-Net on CIFAR-10, CIFAR-100, and ImageNet datasets, our experiments showed that EEEA-Net achieved the lowest error rate among state-of-the-art NAS models, with 2.46% for CIFAR-10, 15.02% for CIFAR-100, and 23.8% for ImageNet dataset. Further, we implemented this image recognition architecture for other tasks, such as object detection, semantic segmentation, and keypoint detection tasks, and, in our experiments, EEEA-Net-C2 outperformed MobileNet-V3 on all of these various tasks. (The algorithm code is available at https://github.com/chakkritte/EEEA-Net). [ABSTRACT FROM AUTHOR]