Search

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]

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]

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]