To address the weight coupling problem, certain studies introduced few-shot Neural Architecture Search (NAS) methods, which partition the supernet into multiple sub-supernets. However, these methods often suffer from computational inefficiency and tend to provide suboptimal partitioning schemes. To address this problem more effectively, we analyze the weight coupling problem from a novel perspective, which primarily stems from distinct modules in succeeding layers imposing conflicting gradient directions on the preceding layer modules. Based on this perspective, we propose the Gradient Contribution (GC) method that efficiently computes the cosine similarity of gradient directions among modules by decomposing the Vector-Jacobian Product during supernet backpropagation. Subsequently, the modules with conflicting gradient directions are allocated to distinct sub-supernets while similar ones are grouped together. To assess the advantages of GC and address the limitations of existing Graph Neural Architecture Search methods, which are limited to searching a single type of Graph Neural Networks (Message Passing Neural Networks (MPNNs) or Graph Transformers (GTs)), we propose the Unified Graph Neural Architecture Search (UGAS) framework, which explores optimal combinations of MPNNs and GTs. The experimental results demonstrate that GC achieves state-of-the-art (SOTA) performance in supernet partitioning quality and time efficiency. In addition, the architectures searched by UGAS+GC outperform both the manually designed GNNs and those obtained by existing NAS methods. Finally, ablation studies further demonstrate the effectiveness of all proposed methods.

Low-light image enhancement (LLIE) aims at restoring the color and brightness of underexposed images. Supervised methods suffer from high costs in collecting paired low-normal light images, while unsupervised approaches require intricate loss functions. To tackle these dual challenges, we propose the Trouble-Maker Learning (TML) strategy, which leverages images with normal light as training inputs. TML comprises two core components. Firstly, the Troublemaker Model (TM) generates pseudo low-light images from normal images, thereby alleviating the need for pairwise data and reducing associated costs. Secondly, the Predicting Model (PM) enhances the brightness of pseudo low-light images. Additionally, we integrate an Enhancing Model (EM) to further refine the visual quality of the PM's outputs. In LLIE tasks, it is crucial to capture global element correlations, as this allows for the extraction of more information pertaining to the same object. Convolutional Neural Networks (CNNs) and self-attention mechanisms are not well-suited to this task due to the local CNN operators, and high time complexity, respectively. To address these limitations, we propose Global Dynamic Convolution (GDC) with a time complexity of O(n). Essentially, GDC mimics the partial calculation process of self-attention to establish element-wise correlations. Building upon the GDC module, we develop the UGDC model. Finally, we explore the application of Data Fusion in the field of LLIE. Based on the Retinex theory, we conducted feature-level fusion using low-light images, illumination components and reflection components, which further enhance the performance of the LLIE system. Extensive quantitative and qualitative experiments demonstrate that UGDC, trained with TML and via data fusion, can achieve performance competitive with state-of-the-art approaches on public datasets. The source code of this paper is publicly available at https://github.com/Rainbowman0/TML_LLIE, facilitating reproducibility of the research findings.

The surprisingly popular decision in social science fields is a wisdom of the crowd technique that taps into the expert minority opinion within a crowd, which has been demonstrated to be remarkably effective for multiple questions. Most of the existing PSO variants construct the exemplars by solely using fitness, which could be viewed as the democratic approaches or methods. However, the democratic methods tend to highlight the most popular opinion, not necessarily the most correct, which might lead the population into a local trapping region in the scenarios of swarm intelligent computing and evolutionary computation. This paper proposes a method to implement the surprisingly popular decision in PSO to facilitate the exemplar construction, cooperating with the dynamic topology maintenance. The proposed PSO variant is called the Surprisingly Popular Algorithm-based Comprehensive Adaptive Topology Learning Particle Swarm Optimization (SPA-CatlePSO). By using the dynamic topological connection and surprisingly popular decision strategy, the proposed SPA-CatlePSO could adjust the degree of small world topology, mimicking the mechanism of knowledge conversion in the crowd, and guide the direction of the exploitation by constructing exemplars with the largest surprisingly popular degree. We evaluate the proposed SPA-CatlePSO on the full CEC2014 benchmark suite and compare its validity with OLPSO, TSLPSO, ASDPSO, HCLPSO, OptBees and L-shade. The experimental results show that the SPA-CatlePSO algorithm is competitive with the most advanced swarm-based intelligent algorithms.

Particle swarm optimizations (PSOs) are drawing extensive attention from both research and engineering fields due to their simplicity and powerful global search ability. However, there are two issues needing to be improved: one is that the classical PSO converges slowly; the other is that classical PSO tends to result in premature convergence, especially for multi-modal problems. This paper attempts to address these two issues. Firstly, to improve the convergent efficiency, this paper proposes an asymptotic predicting model of the globally-optimal solution, which is used to predict the global optimum based on extracting the features reflecting the evolutionary trend. The predicted global optimum is then taken as the third exemplar, in a way similar to the individual historical best solution and the swarm historical best solution in guiding the evolutionary process of other particles. To reduce the probability that the population is trapped into a local optimum due to the premature phenomenon, this paper proposes an adaptive mutation strategy, which is used to help the trapped particles to escape away from the local optimum by using the extended non-uniform mutation operator. Finally, we combine the two entities to develop a globally-optimal prediction-based adaptive mutation particle swarm optimization (GPAM-PSO). In numerical experimental parts, we compare the proposed GPAM-PSO with 11 existing PSO variants by using 22 benchmark problems of 30-dimensions and 100-dimensions, respectively. Numerical experiments demonstrate that the proposed GPAM-PSO could improve the accuracy and efficiency remarkably, which means that the combination of the globally-optimal prediction-based search and the adaptive mutation strategy could accelerate the convergence and reduce premature phenomenon effectively. Generally speaking, GPAM-PSO performs most efficiently and robustly. Moreover, the performance on an engineering problem demonstrates the practical application of the proposed GPAM-PSO algorithm.

A fast algorithm, called the fast Fourier transform on multipoles (FFTM) method, is developed for efficient solution of the integral equation in the boundary element method (BEM). This method employs the multipole and local expansions to approximate far field potentials, and uses the fast Fourier transform (FFT) to accelerate the multipole to local translation operator based on its convolution nature. The series of uncoupled convolutions allows further speed up in the algorithm through parallel computation. In this paper, we present the results of using the FFTM algorithm for solving large-scale three-dimensional electrostatic problems. It is demonstrated that the method can give accurate results with relatively low order of expansion. It is also found that the serial version of the algorithm has computational complexities of O(N/sup a/), where a ranges from 1.0 to 1.4 for computational time, and from 1.1 to 1.2 for memory storage requirement. Significant speedup is also observed in the parallel implementation of FFTM using up to 16 processors on an IBM-p690 supercomputer.

Inspired by the idea of genetic algorithm, we propose two hybrid evolutionary algorithms based on PSO and GA methods through crossing over the PSO and GA algorithms. The main ideas of the two proposed methods are to integrate PSO and GA methods in parallel and series forms respectively. Simulations for a series of benchmark test functions show that both of the two proposed methods possess better ability to find the global optimum than that of the standard PSO algorithm.