In recent years, neural architecture search (NAS) has achieved unprecedented development because of its ability to automatically achieve high-performance neural networks in various tasks. Among these, the evolutionary neural architecture search (ENAS) has impressed the researchers due to the excellent heuristic exploration capability. However, the evolutionary algorithm-based NAS are prone to the loss of population diversity in the search process, causing that the structure of the surviving individuals is exceedingly similar, which will lead to premature convergence and fail to explore the search space comprehensively and effectively. To address this issue, we propose a novel indicator, named architecture entropy, which is used to measure the architecture diversity of population. Based on this indicator, an effective sampling strategy is proposed to select the candidate individuals with the potential to maintain the population diversity for environmental selection. In addition, an unified encoding scheme of topological structure and computing operation is designed to efficiently express the search space, and the corresponding population update strategies are suggested to promote the convergence. The experimental results on several image classification benchmark datasets CIFAR-10 and CIFAR-100 demonstrate the superiority of our proposed method over the state-of-the-art comparison ones. To further validate the effectiveness of our method in real applications, our proposed NAS method is applied in the identification of lumbar spine X-ray images for osteoporosis diagnosis, and can achieve a better performance than the commonly used methods. Our source codes are available at https://github.com/LabyrinthineLeo/AEMONAS.

The abuse of community detection algorithms may bring the risk of privacy leakage. To protect personal privacy in complex networks, community detection attack algorithms are proposed, which can hide the true community structure of the whole network from the community detection algorithms by adding and deleting subtle edges. However, most of the existing algorithms perform attack based on a community structure so that a specific community detection method is usually adopted for obtaining the communities, which causes the algorithms to not perform well when the attacked community detection algorithm is unknown. To this end, a local structure-based community detection attack heuristic approach (LSHA) is proposed in this article, where the local structures, including several nodes with dense connections instead of the whole community structures, are considered. Unlike the whole community structures obtained by different community detection algorithms, which are usually different, the nodes in such a local structure are often assigned into the same community so that the attack is more general for different community detection algorithms. Specifically, in LSHA, a local structure selection strategy is proposed to maximize the attack effect, which selects two local structures for rewiring attack. Furthermore, two metrics, i.e., edge vulnerability and node entropy, are also suggested to select the nodes and edges for attack. In the experiments, the proposed LSHA is compared with five state-of-the-art attack algorithms. The experimental results against five representative community detection algorithms on nine real-world networks show that the proposed algorithm LSHA achieves good performance on both the attack effectiveness and the efficiency.

Recently, researchers pay more attention to designing graph-based methods to address the feature selection problem, since these methods can effectively utilize the underlying topology structure and complex relationships between nodes in the constructed feature graph. Therefore, they can obtain the feature subset with high quality. The existing graph-based methods mainly focus on using different graph-theoretical techniques to select features from the constructed feature graphs. However, little attention is focused on constructing a suitable feature graph for feature selection, which is also an important component for achieving a good feature subset. To fill the gap, in this paper, a novel graph-based algorithm named GBFS-SND is proposed for feature selection, where the structure and node dynamic mechanisms are designed to directly optimize the performance of feature selection. To be specific, in GBFS-SND, a candidate feature graph is firstly created by considering both the importance of feature and the relations between features. Then, on the created candidate graph, an MOEA-based structure dynamic mechanism is suggested to acquire a feature subgraph with better structure, from which we can obtain a promising feature subset. Finally, a node dynamic mechanism is also suggested, with which the weights of the nodes are dynamically adjusted as the structure of feature graph changes. Thus, the performance of GBFS-SND can be further enhanced. Empirical studies are conducted by comparing the proposed algorithm with several state-of-the-art feature selection methods on different data sets. The experimental results demonstrate the superiority of GBFS-SND over the comparison methods in terms of both the accuracy and the number of selected features.

Evolutionary algorithms (EAs) have shown their competitiveness in solving the problem of feature selection. However, limited by their encoding scheme, most of them face the challenge of “curse of dimensionality”. To address the issue, in this paper, an objective space constraint-based evolutionary algorithm, named OSC-EA, is proposed for high-dimensional feature selection (HDFS). Although the decision space of EAs for HDFS is very huge, its objective space is the same as that of the low-dimensional feature selection. Based on this fact, in the proposed OSC-EA, the HDFS is firstly modeled as a constrained problem, where a constraint of the objective space is introduced and used to partition the whole objective space into the “feasible region” and the “infeasible region”. To handle the constrained problem, a two-stage $\varepsilon$ɛ constraint-based evolutionary scheme is designed. In the first stage, the value of $\varepsilon$ɛ is set to be very small, which ensures that the search concentrates on the “feasible region”, and the latent high-quality feature subsets can be found quickly. Then, in the second stage, the value of $\varepsilon$ɛ increases gradually, so that more solutions in the “infeasible region” are considered. Until the end of the scheme, $\varepsilon \rightarrow \infty$ɛ→∞; all the solutions in the objective space are considered. By using the search in the second stage, the quality of the obtained feature subsets is further improved. The empirical results on different high-dimensional datasets demonstrate the effectiveness and efficiency of the proposed OSC-EA.