Guizhen Mai

Knowledge graphs (KGs) organize relational facts in a form that supports machine reasoning across many domains. In decentralized Internet of Things (IoT) environments, such graphs can describe interactions among distributed devices and services. However, privacy constraints, intermittent communication, and incomplete observations can leave the resulting graphs sparse and incomplete. This sparsity weakens path availability and makes missing-fact inference difficult. Multi-hop reasoning can recover unobserved links through explicit reasoning paths, but conventional hierarchical reinforcement learning (HRL) approaches may explore inefficiently when only a few valid paths are available. This paper presents attentiON exploratIon of cluster relatioN (ONION), a framework for sparse KG reasoning. ONION introduces a cluster relation augmentation (CRA) module to add cluster relation cues to the action space, together with a relation-level attention (RLA) mechanism to emphasize relations that are relevant to the query. These components guide hierarchical exploration toward more informative paths. ONION is evaluated on four public sparse-KG benchmarks, and the results show competitive performance with the clearest gains on highly sparse datasets.

Motion deblurring is an ill-posed, challenging problem in image restoration due to non-uniform motion blurs. Although recent deep convolutional neural networks have made significant progress, many existing methods adopt multi-scale or multi-patch subnetworks that involve additional inter-subnetwork processing (e.g., feature alignment and fusion) across different scales or patches, leading to substantial computational cost. In this paper, we propose a novel fully-cascaded spatial-aware convolutional network (FSCNet) that effectively restores sharp images from blurry inputs while maintaining a favorable balance between restoration quality and computational efficiency. The proposed architecture consists of simple yet effective subnetworks connected through a fully-cascaded feature fusion (FCFF) module, enabling the exploitation of diverse and complementary features generated at each stage. In addition, we design a lightweight spatial-aware block (SAB), whose core component is a channel-weighted spatial attention (CWSA) module. The SAB is integrated into both the FCFF module and skip connections, enhancing feature fusion by enriching spatial detail representation. On the GoPro dataset, FSCNet achieves 33.01 dB PSNR and 0.962 SSIM, delivering comparable or higher accuracy than state-of-the-art methods such as HINet, while reducing model size by nearly 80%. Furthermore, when the GoPro-trained model is evaluated on three additional benchmark datasets (HIDE, REDS, and RealBlur), FSCNet attains the highest average PSNR (29.53 dB) and SSIM (0.903) among all compared methods. This consistent cross-dataset superiority highlights FSCNet’s strong generalization and robustness under diverse blur conditions, confirming that it achieves state-of-the-art performance with a favorable performance–complexity trade-off.

Traditional fuzzy clustering algorithms construct sample partition criteria solely based on similarity measures but lack an effective representation of prior membership information, which limits further improvements in clustering accuracy. To address this issue, this paper proposes a semi-supervised fuzzy clustering algorithm based on prior membership (SFCM-PM). The proposed algorithm introduces prior information entropy as a metric to quantify the divergence between partition membership and prior membership and incorporates this as an auxiliary partition criterion into the objective function. By jointly optimizing data similarity and consistency with prior knowledge during the clustering process, the algorithm achieves more accurate and reliable clustering results. The experimental results demonstrate that the SFCM-PM algorithm achieves significant performance improvements by incorporating a small number of prior membership samples across several standard and real-world datasets. It also performs outstandingly on datasets with unbalanced sample distributions.

Multimodal multiobjective optimization problems, characterized by multiple solutions mapping to identical objective vectors, are ubiquitous in real-world applications. Despite their prevalence, most existing multimodal multiobjective evolutionary algorithms (MMOEAs) predominantly focus on identifying global Pareto sets, often overlooking the equally significant local Pareto sets. While some algorithms attempt to address local Pareto sets, their performance in the objective space remains suboptimal. The inherent challenge lies in the fact that a single strategy cannot effectively tackle problems with and without local Pareto fronts. This study proposes a novel approach that first detects the presence of local Pareto fronts using a neural network, thereby enabling adaptive adjustments to the algorithm’s selection strategy and search scope. Based on this detection mechanism, we design a microscale searching multimodal multiobjective evolutionary algorithm (MMOEA_MS). Through extensive experiments on twenty-two benchmark problems, MMOEA_MS demonstrates superior performance in identifying local Pareto fronts and outperforms existing algorithms in the objective space. This study highlights the effectiveness of MMOEA_MS in solving multimodal multiobjective optimization problems with diverse Pareto front characteristics, thereby addressing key limitations of current methodologies.

This paper mainly tends to investigate finite-time stability and stabilization of impulsive stochastic delayed neural networks with randomly occurring uncertainties (ROUs) and randomly occurring nonlinearities (RONs). Firstly, by constructing the proper Lyapunov-Krasovskii functional and employing the average impulsive interval method, several novel criteria for ensuring the finite-time stability of impulsive stochastic delayed neural networks are obtained by means of linear matrix inequalities (LMIs). Then, some conditions about the state feedback controller are derived to ensure the finite-time stabilization of impulsive stochastic delayed neural networks with ROUs and RONs. Finally, numerical examples are provided to demonstrate the effectiveness and feasibility of the proposed results.

In the problem of causal discovery, conditional independence (CI) tests are generally used to detect the causal relationships among observed data. Due to the curse of dimensionality and the limitation of causal direction learning based on V -structure learning, it is difficult for constraint-based methods to distinguish the actual graph from a set of Markov equivalence classes. To alleviate this problem, in this work, a novel regression-based method to test CIs over linear Non-Gaussian data is proposed. The main purpose of this proposal is to relax the CI test of x±yǀZ to two unconditional independence tests x – f (Z)±y – g (Z) + ∑H (Z) and x – f (Z) + ∑H (Z)±y – g (Z), where f and g can be estimated by linear regression independently. In addition, we further show that x – f (Z)±y – g (Z) + ∑H (Z) ( or x – f (Z) + ∑H (Z)±y – g (Z) ) can lead to x← Z ( or y ← Z ). According to this regression-based method, we design a causal structure learning algorithm to learn the actual graph instead of a set of Markov equivalence classes over the observed data. Experiments indicate that our method can detect much more causal relationships than other existing methods, especially in large-scale cases.

Exploring and detecting the causal relations among variables have shown huge practical values in recent years, with numerous opportunities for scientific discovery, and have been commonly seen as the core of data science. Among all possible causal discovery methods, causal discovery based on a constraint approach could recover the causal structures from passive observational data in general cases, and had shown extensive prospects in numerous real world applications. However, when the graph was sufficiently large, it did not work well. To alleviate this problem, an improved causal structure learning algorithm named brain storm optimization (BSO), is presented in this paper, combining K2 with brain storm optimization (K2-BSO). Here BSO is used to search optimal topological order of nodes instead of graph space. This paper assumes that dataset is generated by conforming to a causal diagram in which each variable is generated from its parent based on a causal mechanism. We designed an elaborate distance function for clustering step in BSO according to the mechanism of K2. The graph space therefore was reduced to a smaller topological order space and the order space can be further reduced by an efficient clustering method. The experimental results on various real-world datasets showed our methods outperformed the traditional search and score methods and the state-of-the-art genetic algorithm-based methods.