Stock market volatility research has long been the focus of industry and academia, and stock trend forecasting is challenging. Existing research focuses more on how to aggregate historical price features into graph networks, ignoring the effects of other information such as news and current events on forecasts. Most existing graph-based learning methods create stock graphs by manually constructing stock relationships, ignoring the complexity of stock relationships. Based on these, we propose a novel multilevel graph attention network (ML-GAT) for predicting the stock market trends. To be more specific, we initialize the node representations captured by each feature extraction module, then update the stock nodes in the isomorphic graph converted from Wikidata using ML-GAT, selectively aggregate the information of various relation types, aggregate the information to the node representation, and finally feed the result to a particular forecast layer for forecasting, completing the trend forecast of 423 stocks in the S&P 500 index and 286 stocks in the CSI 300 index. By comparing 5 popular approaches, the experimental research verifies ML-GAT’S state-of-the-art performance in prediction tasks. In comparison with the best performance benchmark model, the F1-score and accuracy increased by 11.82% and 12.6%, respectively, and the average daily return and Sharpe rate rose by 5.06 percent and 94.81 percent, respectively. More significantly, our model’s stock linkages are interpretable and consistent with real-world interactions.

The global interest in environmental protection and sustainable development has grown steadily in recent years, sparking widespread concern about green development in the manufacturing industry among governments, enterprises, and scholars around the world. Despite this heightened interest, research on the influence of the digital economy on the manufacturing industry’s green development remains scarce. This article analyzes the impact of the digital economy on the green development of the manufacturing industry and examines the role of human capital and trade competitiveness in this context. Using a two-way fixed-effects model of panel data analysis, we investigated the GTFP (Green Total Factor Productivity) of the Chinese manufacturing industry, as well as that of the overall industry and 20 other Asian countries along the “Belt and Road”. Our findings indicate a positive association between the digital economy and both the overall GTFP and the manufacturing GTFP in China. The countries situated along the Belt and Road experience a U-shaped trend in their GTFP due to the impact of the digital economy. The digital economy displays a delayed impact, and its eco-friendly value is realized, to different extents, after two sequential periods. In addition, human capital and trade competitiveness are threshold variables in the relationship between the digital economy and the green development of the manufacturing industry. When human capital exceeds a certain threshold and trade competitiveness exceeds a certain threshold, the digital economy has a positive effect on GTFP. This study offers unique insights into the impact of the digital economy on the green development of the manufacturing industry. By addressing this research gap, this study gives policymakers the ability to leverage these findings to promote sustainable practices across the industry. Ultimately, the valuable insights provided by this study may contribute to the ongoing efforts to advance the green development of the manufacturing industry.

In essence, the network is a way of encoding the information of the underlying social management system. Ubiquitous social management systems rarely exist alone and have dynamic complexity. For complex social management systems, it is difficult to extract and represent multi-angle features of data only by using non-negative matrix factorization. Existing deep NMF models integrating multi-layer information struggle to explain the results obtained after mid-layer NMF. In this paper, NMF is introduced into the multi-layer NMF structure, and the feature representation of the input data is realized by using the complex hierarchical structure. By adding regularization constraints for each layer, the essential features of the data are obtained by characterizing the feature transformation layer-by-layer. Furthermore, the deep autoencoder and NMF are fused to construct the multi-layer NMF model MSDA-NMF that integrates the deep autoencoder. Through multiple data sets such as HEP-TH, OAG and HEP-TH, Pol blog, Orkut and Livejournal, compared with 8 popular NMF models, the Micro index of the better model increased by $1.83$, NMI value increased by $12\%$, and link prediction performance improved by $13\%$. Furthermore, the robustness of the proposed model is verified.

Nonnegative matrix factorization (NMF), which is aimed at making all elements of the factorization nonnegative and achieving nonlinear dimensional reduction at the same time, is an effective method for solving recommendation system problems. However, in many real-world applications, most models learn recommendation models under the supervised learning paradigm. Since the recommendation performance of NMF models relies heavily on initialization, the user-item interaction information is often very sparse. In many cases, supervised information about the data is difficult to obtain, resulting in a large number of existing models for supervised learning being inapplicable. To address this problem, we propose an information self-supervised NMF model for recommendation. Specifically, this model is based on the matrix factorization idea and introduces a self-supervised learning mechanism based on the NMF model to enhance the sparse data information of sparse data, and an easily extensible self-supervised NMF model was proposed. Furthermore, a corresponding gradient descent optimization algorithm was proposed, and the complexity of the algorithm was analysed. A large number of experimental results show that the proposed S²NMF has better performance.

A mobile communication network usually has a complex system composed of millions of connected mobile devices, each device can be regarded as a node, and the communication between them can be regarded as an edge. Because the structure of mobile communication networks always changes with time, such as the appearance or disappearance of device nodes or edges, the traditional method of researching mobile communication network structure modelling becomes a very challenging problem. This paper constructs a dynamic community detection model based on representation learning (DCDAL) based on graph autoencoding and the Gaussian mixture depth model in response to the above problems. Commonly used dynamic network evaluation indicators such as NMI and modularity are compared and analyzed in complex communication networks. The DCDAL model can outperform the optimal comparative models in NMI and other indicators, especially in large-scale mobile communication network datasets. The model can obtain robust results on multiple indicators Text for this section.